#image

94 articles

01 ·Time Series·★ MEMBER·PAPER·7 min read Paper Explained: Video Generation Models: A Survey of Post-Training and Alignment — Four Toolboxes for Making Video Models Do What You Ask A from-scratch reading of the survey that organizes how pretrained video generators are steered toward instruction-following, temporal coherence, physical plausibility, and safety without retraining—via supervised fine-tuning, self-training and distillation, preference and reward optimization, and inference-time methods. 02 ·★ MEMBER·PAPER·7 min read Paper Explained: WorldCrafter — A Video World Model That Remembers What You Saw, via Camera-Queryable Memory Video world models tend to repaint a room differently when you walk back into it. WorldCrafter tackles this with an implicit 3D-aware memory that is read out from the viewpoint you are about to look from. We explain it from scratch with equations, interactive figures, and code. 03 ·Inference & Serving·★ MEMBER·PAPER·8 min read Paper Explained: RewardVerse — A Video Reward Model That Writes the Rubric Before It Scores (RGPO) Video reward models tend to squeeze their scores into a narrow band, and those scores move when the wording changes. The paper calls this scalar drift. RewardVerse first generates an evaluation rubric, then reads a continuous score for each item from token probabilities. Its two-stage RGPO training uses only 30 preference pairs per dimension. 04 ·Paper Deep-Dives·★ MEMBER·PAPER·10 min read Paper Explained: RayOrch — Batching Children Across Parents on GPUs Without Losing Track of Who Owns What Split PDFs into pages and videos into clips, batch them across sources on GPUs, and still route every result back to the right parent in the right order. A from-scratch walkthrough of RayOrch: its vocabulary, state machine, commit rule, and measured results. 05 ·★ MEMBER·PAPER·7 min read Paper Explained: Realtime-Venus — A Voice-and-Video Assistant That Keeps Talking While Work Runs in the Background Listening, speaking, and background delegation all share one clock ticking once per second. We walk through the 9B models and the harness that let an assistant hand off tool calls without pausing the conversation, from analogy to equations to pseudocode. 06 ·★ MEMBER·PAPER·10 min read Paper Walkthrough: MaP-WAM — Turning a Robot's Memory into Plans So the Executor Stays the Same Size as History Grows For robot tasks you can't solve without remembering the past, MaP-WAM stops feeding the executor the full video history and instead compresses it into a plan for what to do next. The executor predicts its own progress alongside actions to decide when a step is done. We walk through the design, which reports 83.3% on RMBench and 78.0% on real robots, straight from the paper. 07 ·★ MEMBER·PAPER·8 min read Paper Explained: Can MiniMax-H3 Reason About the Physical World? Testing an Omni-Modal Generator on What the Prompt Leaves Out An evaluation paper that gives MiniMax-H3 — a generator that takes text, images, audio and video together — 517 tasks where the answer is never in the prompt and can only be worked out by combining the inputs. Overall success is 41.97%, and telling events apart by sound manages just 27.40%. 08 ·★ MEMBER·PAPER·8 min read Paper Explained: LIT — Stopping Robots from Cheating on Visual Cues by Giving Vision a Single Doorway Robot foundation models learn to lean on irrelevant cues like backgrounds and lighting. LIT first teaches goal-directed motion without images, then lets vision reach the action expert only through pose-predicting latent tokens — improving LIBERO-Plus success on all four architectures tested. 09 ·Training & Alignment·★ MEMBER·PAPER·8 min read Paper walkthrough: WanPE — turning a video prompt into a director's shooting plan WanPE rewrites a one-line request into a shot-by-shot plan covering camera, lighting and sound. We explain, from zero, why it builds training pairs backwards from real videos and how SC-GRPO penalizes dropped requirements. 10 ·★ MEMBER·PAPER·7 min read Paper Explained: SpatialBlock — Teaching Vision-Language Models Spatial Sense with 15,000 Block-Stacking Puzzles A paper that improves spatial reasoning in vision-language models using nothing but 15,000 synthetic block-stacking questions — no real-scene 3D labels. We walk through how the data is built, the two training recipes, what actually helped, and where it falls short. 11 ·★ MEMBER·PAPER·6 min read Paper Explained: Mi-Ripple — Diagnose First, Then Repair the Ripple That Iterative AI Editing Leaves Behind Feed an AI-edited image back in as the reference for the next edit, and grid-like and grainy texture — digital ripple — starts to build up. Mi-Ripple first tells apart a lattice you can cut out in the frequency domain from grain tangled up with the picture, then picks either a notch filter or regeneration from a cleaned reference. 12 ·Large Language Models·★ MEMBER·PAPER·8 min read Paper Explained: Training Object Permanence in World Models — Teaching Video Models That Hidden Things Still Exist Video generators make hidden objects vanish and let balls pass through walls. We walk through WROP, a 150-task Blender benchmark for object permanence and solidity, the 16B PWM-WROP model fine-tuned on it, and how to read the human-preference evaluation behind the results. 13 ·★ MEMBER·PAPER·8 min read Paper Explained: SenseNova-U1.5 — One Model That Both Sees and Draws, With No Encoder and No VAE SenseNova-U1.5 is an 8B unified model that learns straight from pixels and words, with no vision encoder for understanding and no VAE for generation. We walk through its seam-free spatial decoder and its 'train specialists separately, then distill them into one' post-training, following the paper itself. 14 ·RAG & Retrieval·★ MEMBER·PAPER·7 min read Paper Explained: Ovis-Embedding — One Ruler for Text, Images, Video, and Audio A from-scratch walkthrough of Ovis-Embedding, a model family that puts text, images, video, and audio into one vector space: the four-stage training recipe, the trick that keeps accuracy when you shorten the vectors, and what the paper does not show. 15 ·RAG & Retrieval·★ MEMBER·PAPER·7 min read Paper Explained: D-RAC — Normalize Everything to PDF, Read the Pages Once, Then Chunk by ID D-RAC ingests PDFs, Word files and slides for RAG by rendering everything to PDF, converting the pages to Markdown with one multimodal LLM pass, and then letting an LLM plan chunks using only element IDs. Explained from scratch. 16 ·Inference & Serving·★ MEMBER·PAPER·6 min read Paper Explained: IntBMoE — Every Expert Contributes, Yet Each Token Runs Only a Few Blocks In a Mixture-of-Experts layer, how many experts inform a token, how many get computed, and how many weight sets must be built have always been tied together. IntBMoE (arXiv:2609.21346) cuts those ties by composing experts densely and executing blocks sparsely. Explained from scratch, using only the paper itself. 17 ·★ MEMBER·PAPER·11 min read Paper Explained: VDiff-Bench — Even Frontier MLLMs Miss the Low-Level Changes in a Spot-the-Difference Puzzle VDiff-Bench asks a multimodal LLM what changed between two near-identical images, as a four-way multiple choice. We walk through how its 1,756 questions across 10 change categories were built, what 11 models scored, why several of them answer 'no difference' when noise or texture changed, and what this means if you use an MLLM to grade image edits. 18 ·★ MEMBER·PAPER·13 min read Paper Explained: Reason Through the Latent! — Visual information being in a latent state doesn't mean the answer uses it Several latent visual reasoners keep their accuracy even when you corrupt the latent state — the answer is not actually flowing through it. CVRR (arXiv:2609.06746) starts recurrence from the question state after the image has been absorbed, then closes every other image-conditioned route before decoding, making latent computation necessary while keeping performance. A walkthrough grounded only in the paper's text, including its causal interventions. 19 ·★ MEMBER·PAPER·11 min read Paper Walkthrough: SceneMosaic — Physically Valid 3D Rooms from One Image, in Minutes, in Many Variations How to turn a single picture of a room into a simulation-ready 3D scene with zero collisions, in minutes rather than hours, and with several coherent furniture rearrangements thrown in. A walkthrough of how SceneMosaic stitches the speed of image-to-3D models to the precision of VLM agents, with the equations and interactive figures. 20 ·★ MEMBER·PAPER·17 min read Paper Walkthrough: Miles v0.1 — Anatomy of a Post-Training Stack Built to Survive Production A read-through of Miles, a full-stack system for agentic RL post-training of frontier MoE models: how it hunts down the numerical drift between the rollout engine and the trainer, and what a 744B model actually measured on 64 GPUs. 21 ·★ MEMBER·PAPER·12 min read Paper Deep Dive: Mask Forcing — Fixing Autoregressive Video Diffusion Distillation with a Dual-Noise Mask Distilling a bidirectional video diffusion teacher into a real-time autoregressive student tends to produce over-saturated, over-smoothed video. Mask Forcing eases this mode collapse by randomly swapping some tokens in the student's own rollout for slightly cleaner ones — no real data, no extra post-training stage. 22 ·★ MEMBER·PAPER·9 min read Paper Walkthrough: Marigold V2 — Turning an Image Editor Into a State-of-the-Art Depth Estimator on One 32GB GPU How Marigold V2 repurposes an image-editing diffusion transformer (Qwen-Image-Edit) into a state-of-the-art monocular depth estimator using QLoRA and two new losses — explained from first principles through normalization, single-step inference, iREPA, and SinkLoss. 23 ·★ MEMBER·PAPER·8 min read GE-Act 2.0 Paper Explained: Pretraining and Scaling a World-Action Model for Robotic Manipulation GE-Act 2.0 is a world-action model trained from scratch on manipulation data instead of inheriting a video generator. We walk through its single-step visual planner, the KASO rule that keeps only futures compatible with the recorded action, and what 100 zero-shot tasks actually showed. 24 ·★ MEMBER·PAPER·13 min read Paper Walkthrough: ENEAS — Telling Real Instances From Their Doppelgangers Ask for 'person' and you get the statues too. This paper fixes the failure where a mask is geometrically right and semantically wrong, using an embedding filter plus a conditional VLM judge — explained from first principles. 25 ·Agents·★ MEMBER·PAPER·11 min read Editable Visual Design, explained — demoting image generation to a sketch and shipping the artifact as HTML The image model stops being the deliverable and becomes an imagination engine plus an asset factory, while a coding agent rebuilds the piece in HTML/CSS. A walk through the paper behind posters whose layers come apart and whose text is real text. 26 ·★ MEMBER·PAPER·10 min read Paper Walkthrough — Beyond Retrieval: LatentStream Turns Retrieved Video Into Latent Memory For never-ending video streams, LatentStream stops appending retrieved evidence as extra context and instead internalizes it into fixed-length latent memory tokens. A ground-up walkthrough of its hierarchical memory, latent evolution, and confidence-driven test-time optimization. 27 ·★ MEMBER·PAPER·9 min read Paper Walkthrough: The Design Fundamentals of Pixel Text Representation Learning An encoder that reads meaning straight off the pixels, never converting glyphs to character codes. This EMNLP 2026 paper argues that what decides its quality is not data volume but four design choices — explained from zero. 28 ·★ MEMBER·PAPER·16 min read Paper Walkthrough — The Missing Temporal Link: Putting Script Timing on the Video–Audio Axis with Temporal Context Routing Video and audio stay in sync with each other while both drift off the script's timeline. This walkthrough follows the paper's own equations and numbers to show how TCR closes that third, missing temporal link with a single additive term in the cross-attention logits. 29 ·Paper Deep-Dives·★ MEMBER·PAPER·11 min read Paper Walkthrough — RoboTok: Mining the Web for Demonstrations That Move Like Yours A ground-up walkthrough of RoboTok (arXiv:2609.03199), a data engine that pulls manipulation-relevant human demonstrations out of web video. Covers how DTW defines 'similar motion', how that ranking is distilled into an embedding for inner-product search, and what the results do and don't show. 30 ·★ MEMBER·PAPER·10 min read Paper Walkthrough: Puffin-World — A World Model That Remembers Which Way Is Up What changes when you give an image generator a sense of gravity? A ground-up walkthrough of Puffin-World's Omni-Camera representation and physics propagation, with equations and interactive figures. 31 ·★ MEMBER·PAPER·9 min read Paper Walkthrough: LLaDA-Image — Building the Visual Prior from Images Alone, Then Distilling to 2–4 Steps A training recipe that builds the visual prior from images alone before any caption enters the picture. We walk through LLaDA-Image — a 6B DiT trained from scratch and distilled down to 2–4 sampling steps — following the design decisions the paper actually makes. 32 ·Inference & Serving·★ MEMBER·PAPER·12 min read Paper Explained — LatentPress: Feeding Compressed Context Straight to a Frozen LLM, Neither as Text Nor as Pixels A method that writes long conversation histories and documents into continuous memory tokens a frozen LLM reads directly — no text summary, no rendered image. On LongMemEval it beats uncompressed evidence at 7.70x compression. Explained from first principles. 33 ·★ MEMBER·PAPER·14 min read SolarWM: Training on 5 Seconds, Walking for an Hour — and Opening the Whole Stack A data engine that folds 10 datasets into 1.43M clips under one contract, plus a three-stage recipe that adapts four different video backbones without erasing them. The causal models roll out for minutes to hours after training on 5-second sequences alone. 34 ·Agents·★ MEMBER·PAPER·13 min read Paper Walkthrough: ZimaBlue — Turning 120,000 Hours of Egocentric Video into Robot Skill A ground-up walkthrough of the World Action Model that converts 120,000 hours of action-free egocentric video into robot control: a three-stage curriculum, a 100-D unified action interface, and an asynchronous Slow-Fast pair that takes zero-shot success from 36.1% to 77.8% at a 33 ms control loop. 35 ·Agents·★ MEMBER·PAPER·10 min read Paper Walkthrough — UrbanGround: Where MLLM Agents Break Down on a Real Street Drop an MLLM agent into a real-scale replica of Hong Kong built from territory-wide 3D geospatial data. Visual recognition clears 90%, orientation sits near 40%, long-range navigation is close to 0%. A walkthrough of the benchmark that measures the gap between seeing and moving. 36 ·Agents·★ MEMBER·PAPER·13 min read Paper Walkthrough: UI-Venus-2 — Taking Screen-Operating Agents From Benchmarks to Real Work A ground-up read of the UI-Venus-2 Technical Report: a GUI agent that drives phones, browsers and desktops from pixels alone. What it scales, how it verifies its own training data, and where it still falls short. 37 ·★ MEMBER·PAPER·14 min read Paper Walkthrough: Eleven Frames Are Enough — Revisiting Local Context for Long-Horizon Streaming 3D Reconstruction How do you track a camera and rebuild a scene from a video that never ends? ABot-Recon throws away long-range memory entirely and bets on the last twelve frames. A ground-up walkthrough of the paper. 38 ·★ MEMBER·PAPER·12 min read Paper walkthrough: Qwen-Drive-1.0 — bolting 3D perception and planning onto a VLM without touching its architecture Leave the pretrained VLM exactly as it is, attach a BEV perception head and a Planning Expert, and you get 3D detection, occupancy, maps and trajectory generation in one model — general vision-language ability nearly intact, 90.7 PDMS on NAVSIM. A ground-up walkthrough, straight from the paper. 39 ·Time Series·★ MEMBER·PAPER·12 min read H3-World: Turning Language Understanding into World Control — Paper Explained H3-World turns a 33B video generator into a controllable world model without bolting on an action module: express actions as sentences, bind each sentence to a video-latent interval, and use attention routing to stop the crosstalk. Only 0.199% of parameters are trained. 40 ·Agents·★ MEMBER·PAPER·14 min read Paper Walkthrough: Code World Model — Putting a Coding Agent in Charge of the World A ground-up reading of Code World Model, which hands the *evolution* of a world to executable code and its *appearance* to a video model — including the proxy interface that joins them, and the limits the authors admit to. 41 ·Agents·★ MEMBER·PAPER·13 min read Paper Walkthrough: Code as Worlds — An Agent That Writes the World Down as Runnable Code A close read of Code-as-World, which represents physical worlds as executable code and searches for world hypotheses through a propose–execute–render–verify loop. The three parts of an EWR, the agentic discovery loop, the QuantiPhy results, and the limits the paper itself admits. 42 ·★ MEMBER·PAPER·21 min read Lucida, explained — turning a room video back into parts you can move, by deferring precision to the end A system that rebuilds a real indoor scene from video as individually movable 3D assets. It keeps the parse–generate–place order but redistributes what each step is allowed to demand, and hands the final placement to a VLM policy that operates a 3D editor in a closed loop. 43 ·★ MEMBER·PAPER·14 min read Paper Walkthrough: DreamX-Creator — Making Sound and Picture Together in 7B, Then Finishing at 2K in One Step A ground-up walkthrough of a 7B model that denoises audio and video inside one generative process: the gated cross-modal attention, the modality-aware reinforcement learning, the one-step 2K refiner — and the unusually heavy caveats the authors put on their own results. 44 ·★ MEMBER·PAPER·13 min read Paper Walkthrough: GameWAM — Generating the Next Frame and the Next Keystroke Together A ground-up walkthrough of the first World–Action Model for native closed-loop game and GUI control: how it plans 16 actions but commits only 8, and how low-frequency noise in the sampled action source quietly spins the camera. 45 ·★ MEMBER·PAPER·10 min read Paper Explained: Beyond Data Scaling — Why the Backbone, Not the Trajectory Count, Decides Your VLA (VLAct) Robot trajectories can't be scraped off the web, so the paper argues you should squeeze reusable representations out of the trajectories you do have. Three modest interventions — preserving the VLM prior, co-supervising with multiple action heads, and partially unifying the action space across embodiments — beat industrial VLA systems on fully open data and 16 GPUs. 46 ·Training & Alignment·★ MEMBER·PAPER·10 min read PAWBench Explained — Can Video Generators Get the Odds Right, Not Just the Physics? If a video generator is a world model, it owes you more than one plausible rollout — it owes you the right distribution over futures. PAWBench measures that probabilistic alignment across 50 scenarios and 11 systems, and finds that no model gets all the requirements at once. 47 ·FREE·PAPER·9 min read Paper Explained: VGI-Bench — Can Video Models Get the Middle of the Story Right? A ground-up walkthrough of VGI-Bench, a benchmark that treats video generation models as machines that reason in pictures. Even the strongest model, Seedance 2.0, scores only 51.0 — and self-correction during denoising almost never happens. 48 ·FREE·PAPER·15 min read Paper Explained: VBVR-Pro — Making "Thinking in Pictures" Trainable, Scorable, and Comparable Native visual reasoning treats image and video generation as the medium of thought. VBVR-Pro supplies 300 procedurally generated tasks and deterministic scorers that replace the VLM judge, then pits image, video, and interleaved generation against each other on identical ground. Written for readers starting from zero. 49 ·Paper Deep-Dives·★ MEMBER·PAPER·13 min read Paper Walkthrough: Turning Game Development into a Verifiable Trajectory Data Engine — RLHEV and AWoMo A paper arguing that what world models lack is not data or compute but cheap grading. We work through RLHEV — post-training on game-engine checks fused with developer accept/reject decisions — from first principles to equations, interactive figures, and the reported numbers. 50 ·RAG & Retrieval·★ MEMBER·PAPER·13 min read Paper Walkthrough: WeMM-Embedding — Putting Text, Images and Video on One Ruler A walkthrough of WeMM-Embedding (2B/4B/9B), Tencent's universal multimodal embedding family. The unified pair format, the <embedding> token, Matryoshka dimensions, two-stage training and distillation — explained from scratch, using only the numbers the paper reports. 51 ·FREE·PAPER·11 min read Paper Walkthrough: TLive-Omni — An Omni-Modal Model That Watches, Listens, and Tells You the Timestamp A from-scratch walkthrough of TLive-Omni, an omni-modal understanding model built for e-commerce live streaming: Per-vGrid timestamped audio-video interleaving, a three-stage SFT recipe, and Faithful-RFT, which rewards answer faithfulness instead of visible reasoning — grounded strictly in the paper's own numbers. 52 ·FREE·PAPER·10 min read Paper Walkthrough: GigaBrain-0.7 — 37,000 Hours of Embodied Experience and a Three-System Robot Brain A ground-up walkthrough of GigaBrain-0.7, which splits a robot foundation model into understanding, prediction/evaluation, and action, then pretrains it on 37,256.98 hours of embodied data in a single stage. Covers subgoal-image and progress-value conditioning, Soft Knowledge Insulation, and the real-robot numbers — strictly from the paper. 53 ·Agents·★ MEMBER·PAPER·12 min read Paper Walkthrough: Embodied-Navigator (TAMP-Nav) — Let the VLM Just Point, and Navigation Gets Both Faster and Better Instead of asking a VLM for 3D coordinates, have it point at a 2D pixel; think and store memory only at key nodes; align it all with two-level GRPO. A ground-up walkthrough of the design that hits 66.2% SR on R2R-CE at 16.58s per task using only 90k training trajectories. 54 ·FREE·PAPER·15 min read Paper Walkthrough: EchoWM — A World You Can Walk Into, and Hear, Driven by Camera Intent Hand it a reference view and a stream of 'where I want to go', and it keeps generating 720p video together with environmental sound, music and speech. A walkthrough of EchoWM from the paper itself: one camera-intent interface for both first and third person, a single translation scale shared across the whole dataset, and the sink-plus-FIFO cache that makes long rollouts possible. 55 ·FREE·PAPER·9 min read Paper Walkthrough: Annotations as Rollouts — Dropping the Ground Truth Into the Group as a Ninth Answer RL post-training for video MLLMs starves because sampled rollouts almost never contain the right answer. OraRL adds the annotation itself to the group as an extra rollout, then repairs the advantage inversion that naive mixing causes. 56 ·FREE·PAPER·12 min read 4DAnyone, Explained — Turning One Casual Video Into a 4D Person How 4DAnyone builds a free-viewpoint 4D human from a single phone video, explained from scratch. The core trick is not a better generator but two fixes — RCP and TCR — for a context that no longer fits in one attention pass. 57 ·FREE·PAPER·11 min read Paper Walkthrough: SemComp-Bench — Asking Video Generators 'So Did It Actually Get Done?' SemComp-Bench moves video-generation evaluation from 'does it look good' to 'did it reach the outcome I asked for'. A walkthrough of the task definition, the four-stage data pipeline, the AND-vs-average scoring, and the measured numbers — all from the paper itself. 58 ·FREE·PAPER·12 min read Paper Review: S²VOPD — Don't Strengthen the Teacher, Blur the Student's View A walkthrough of S²VOPD, which improves vision-language models without labels, rewards, or a stronger teacher. The trick is inverting where the asymmetry comes from: degrade the student's view instead of privileging the teacher's. 59 ·Agents·★ MEMBER·PAPER·11 min read Paper Walkthrough: OmniScientist — An AI Scientist That Actually Looks at the Raw Data Automating every step of the research workflow doesn't help much if the only thing the agent ever sees is somebody else's summary table. OmniScientist puts raw waveforms, images and 3-D point clouds in front of the agent for the whole research lifecycle and enforces the gates in Python — walked through from the paper itself, up to the 21.7% finding buried in a seismic benchmark. 60 ·Agents·★ MEMBER·PAPER·12 min read Paper Explained: Co-RL — Reasoning Without Labels, Emerging From a Diverse Cohort Grade your own answers long enough and the model collapses. Co-RL breaks that loop by rewarding each agent against a peer's majority vote, matching supervised training without touching a single ground-truth label. The mechanism, the dynamics, the numbers, and the traps — straight from the paper. 61 ·Large Language Models·★ MEMBER·PAPER·8 min read Paper Walkthrough: Can Anything Catch a Fake Crisis Video? — What RA-Bench Found Sixteen thousand AI videos, each continuing from the real first frame of a genuine disaster or war clip, put against seven classical detectors, ten zero-shot multimodal models and two purpose-built fine-tunes. None of them generalized. One model turned out to be reading timestamps rather than pixels, and a lap through a social feed drops fake recall to 1.4%. 62 ·VLMs & Multimodal·★ MEMBER·PAPER·8 min read How VLMs Came Together — Wiring a Vision Encoder into an LLM A vision-language model is three parts: a vision encoder, a projection layer, and an LLM. From the bridge CLIP built, through the three schools of connector design, to resolution strategies and the implementation constraints that bite in practice. 63 ·Agents·★ MEMBER·PAPER·9 min read Paper Explained: Video-DeepResearch — Agents That Watch a Video, Then Chase Down Every Lead A walkthrough of Video-DeepResearch, which pulls visual clues out of a video and corroborates them with web search. We follow the primary source to see how two failure modes — a modality bias that makes models dodge visual tools, and knowledge leakage that lets them answer from memory alone — are beaten with stage-wise tool unlocking and a two-phase SFT + GRPO recipe. 64 ·CNNs & Image Recognition·★ MEMBER·PAPER·8 min read Paper Walkthrough: TurboVLA — Kick the LLM Out of the Loop and Run a Robot Policy at 32 Hz on an RTX 4090 with Under 1 GB of VRAM Mainstream VLA models route every control step through a large language model. TurboVLA removes the LLM and fuses vision and instructions with lightweight bidirectional cross-attention instead — hitting 97.7% on LIBERO with 0.2B parameters, 31.2 ms latency, and 0.9 GB of VRAM. A from-scratch walkthrough of the paper. 65 ·FREE·PAPER·10 min read Paper Deep-Dive: The 'Physics' of Multimodal Pretraining — Which Way Does Knowledge Actually Flow? What happens when a single model learns text and images together from day one? A large-scale controlled study from Meta FAIR and collaborators maps the asymmetric flow of knowledge between modalities, the conditions for synergy, the 'vision laziness' caused by late integration, and a recipe that gets strong image generation from just 5% of the data budget. 66 ·Agents·★ MEMBER·PAPER·8 min read Paper Walkthrough: ToolArtist — Search, Draw, or Redraw? The Image Agent That Decides for Itself Drawing "a harvester collecting dragon's blood resin on Socotra in 1955" correctly takes less artistic skill than research. ToolArtist makes searching, reasoning, and drawing all actions of a single policy — a fully agentic image generator. We walk through the conversion trick behind its SFT data, the dual-reward RL scheme (RAD-GRPO), and the 0.79 WISE result, straight from the paper. 67 ·Audio & Speech·★ MEMBER·PAPER·10 min read Paper Walkthrough: SwanTale — Designing Voices from Words Alone, with Speech and Sound in One Waveform ByteDance's SwanTale handles two jobs in one model: cloning a voice from reference audio (zero-shot) and building voices, ambience, and sound effects purely from a natural-language caption (instruct). We walk through the paper, from the 70M-caption data pipeline to Unified MoE routing and GRPO post-training. 68 ·Agents·★ MEMBER·PAPER·10 min read Paper Walkthrough: Qwen-UI-Agent — How Alibaba Built a GUI Agent That Works on Real Phones and PCs A guided tour of Alibaba MAI-UI team's technical report on Qwen-UI-Agent: a foundation GUI agent trained on 100+ physical phones, a hybrid GUI+CLI action space, and online RL over 100+ turn trajectories, reaching 92.2% on a real-device benchmark. 69 ·CNNs & Image Recognition·★ MEMBER·PAPER·10 min read Paper Walkthrough: PhiZero — A World Model That Reasons in a Language of Physics Before It Renders A close read of PhiZero, which reasons about how the world will change in a discrete 'physical language' learned self-supervised from video, and only then renders the footage — instead of predicting pixels directly. The two-stage tokenizer and reasoner, the top spot on Physics-IQ Verified, zero-shot motion transfer, and the limitations the paper itself admits. 70 ·Agents·FREE·PAPER·10 min read Paper Explained: OSReward — Can You Trust the AI That Grades AI? Remeasuring Rewards for Computer-Use Agents The VLM judges that decide whether an agent driving a PC or a phone succeeded turn out to share a leniency bias that reads failure as success — a paper that exposes it with 1,019 human-verified trajectories and closes the gap with OS-Shepherd, an open reward model 30–60× cheaper, explained from zero background. 71 ·CNNs & Image Recognition·★ MEMBER·PAPER·9 min read Object Detection from Scratch (from YOLO to DETR) A from-zero guide to object detection: the classic toolkit of two-stage detectors, anchors, and NMS — and how DETR reframed the whole problem to make all of it unnecessary. Primary source: the DETR paper. 72 ·Agents·FREE·PAPER·9 min read Paper Walkthrough: Mental World Modeling — A World Model That Advances Minds, Not Just Physics You can track a scene's physics perfectly and still get the next human action wrong. A walkthrough of Mental World Modeling (MWM), which carries beliefs, intentions, emotions and norms as state variables so that every action updates physics and mind together — plus Mentis, the training-free baseline, and its numbers across eight models, straight from the paper. 73 ·CNNs & Image Recognition·★ MEMBER·9 min read Medical Imaging AI — Validation Design Comes Before the Accuracy Number An AI that scored beautifully on your own hospital's data turns out to be useless at the hospital next door — a failure that has been reported over and over in medical imaging. Sensitivity and specificity, the way prevalence flips the meaning of a positive result, internal versus external validation, what site-to-site variation actually is, and what regulators are really reviewing: building up, from first principles, the habit of questioning the validation design before the accuracy figure. 74 ·FREE·PAPER·8 min read Paper Explained: JoyAI-Video-Edit — Autoregressive Diffusion That Keeps Editing 720p Video at ~30 FPS, Without Ever Seeing the Future Say 'swap the background for snowy mountains' and the live feed comes back edited as it streams — a walkthrough of JD's JoyAI-Video-Edit from the paper itself. We trace the three-stage recipe (chunk-wise autoregression, Source-Anchored DMD, long-horizon distillation) that lets a 16B model edit 720p video at roughly 30 FPS. 75 ·FREE·PAPER·8 min read Paper Walkthrough: Hunyuan3D-Buffalo 1.0 — One Brain for 3D Understanding, Generation, and Editing Describe a 3D shape in words, generate it from text, edit it by instruction, carve out a named part — Tencent Hunyuan's Hunyuan3D-Buffalo 1.0 does all four in a single model. We walk through the 87M-sample data factory behind it, the Nano3D-v2 editing-pair pipeline, and the paper's most practical finding: training generation makes editing better. 76 ·Video Codecs·FREE·7 min read From H.264 to AV1 — What a Codec Generation Change Really Involves H.264 has ruled video for two decades; AV1 arrived promising royalty-free efficiency. We unpack the transition along three axes — coding efficiency, compute cost, and licensing — and end with a practical framework for deciding which codec to ship, starting from zero background. 77 ·FREE·PAPER·8 min read Paper Walkthrough: GST-Bench — Can VLMs Build a Global Map of a Scene from Video? Show a VLM a walkthrough video of a house, then ask 'from where you're standing now, which way is the sofa?' — even the strongest model scores barely half of what humans do. A walkthrough of GST-Bench from ByteDance Seed: the shortcut-proof benchmark design, results across 22 models, and the training data that closed 27 points of the gap. 78 ·Agents·FREE·PAPER·9 min read End-to-End Driving from Scratch — Perception to Control in a Single Network End-to-end autonomous driving learns everything from camera pixels to steering in one neural network. Starting from zero, we cover how it differs from the modular stack, imitation learning and distribution shift, why 'predicting the average' causes crashes, and why interpretability and validation remain the hard part. 79 ·Media in Production·★ MEMBER·7 min read How to Read Encoder Settings — What CRF, Presets, and 2-Pass Actually Change The flags in an ffmpeg command — -crf 23, -preset slow, -pass 2 — each answer a different question: what to hold constant (CRF), how hard to search (preset), and whether to read the whole video first (2-pass). We derive why each knob works from the quantization-step formula and rate-distortion optimization, then land on copy-paste-ready commands and the mistakes that bite in production. 80 ·FREE·PAPER·9 min read Paper explained: DEFT-RLVR — show a driving VLM the future trajectory too early and it fabricates its reasoning Let a teacher model peek at the ground-truth trajectory while writing chain-of-thought annotations for driving, and severe hallucinations double from 29% to 50% — the paper calls this trajectory anchoring bias. This article walks through AD-MCQ, which turns planning into a verifiable multiple-choice task, and DEFT-RLVR (arXiv:2608.01755), which reveals trajectories only after the model commits to a decision, using nothing but the paper itself as the source. 81 ·CNNs & Image Recognition·★ MEMBER·PAPER·8 min read The CNN Family Tree — From AlexNet to ResNet and EfficientNet A decade of CNNs told as two campaigns — the race for depth and the race for efficiency. ReLU, residual connections, and compound scaling explained from scratch with metaphors, interactive figures, and code. 82 ·CNNs & Image Recognition·FREE·9 min read The Autonomous Driving Perception Stack from Scratch — What Cameras and LiDAR Each Bring to the Table How a self-driving car figures out what is around it, starting from sensor physics. We cover the complementary strengths of cameras and LiDAR, the bird's-eye-view grid where all sensors meet, occupancy grids grown by Bayesian updates, and the tug-of-war between safety requirements and compute budgets — no prior knowledge assumed. 83 ·FREE·PAPER·9 min read Paper Walkthrough: AURORA-LM — A Diffusion Language Model That Keeps Its Text Latent Full-Width Instead of Compressing It A walkthrough of AURORA-LM, a continuous-latent diffusion language model that rejects the usual compromise of compressing text latents to make diffusion easier. It keeps a decodable, width-1024 latent and learns its distribution with a low-rank input pathway, width-calibrated noise, and self-trajectory consistency. 84 ·CNNs & Image Recognition·★ MEMBER·11 min read Anomaly Detection from Scratch — Learning From Normal Alone Why an AI can learn from good units alone on a factory floor where defect samples barely exist. Two rulers — reconstruction error and density estimation — built up from metaphor to equations, all the way to the part that decides everything in practice: choosing the threshold. 85 ·VLMs & Multimodal·★ MEMBER·PAPER·8 min read BEV Representations From Scratch — Fusing Multiple Cameras Into One Top-Down Map How a self-driving car turns six camera feeds into a single top-down map. Starting from perspective projection, we build up to the two big design philosophies: LSS, which pushes features into 3D via a predicted depth distribution, and Transformer-style methods like BEVFormer that pull information with BEV queries. 86 ·Paper Deep-Dives·FREE·PAPER·8 min read Paper Walkthrough: Alpamayo — NVIDIA's Reasoning Model for Autonomous Driving A first-principles read of NVIDIA's driving VLA Alpamayo-R1: the Chain of Causation dataset that structures reasoning as cause and effect, flow-matching trajectory decoding that fits in 99 ms, and the three-stage training recipe that uses RL to punish gaps between what the model says and what it drives. 87 ·VLMs & Multimodal·FREE·PAPER·7 min read Paper Deep Dive — ViT: Treating an Image Like a Sentence A reading of the ViT paper (Dosovitskiy et al., 2020/2021) grounded strictly in its own text: the move of treating 16x16 patches as words, what the position-embedding ablation actually showed, the price of dropping the convolutional inductive bias, and how conditional the claim 'beats CNNs at scale' really is. 88 ·Generative Models·FREE·PAPER·9 min read Diffusion Models from the Ground Up — Add Noise, Then Subtract It A reading of the DDPM paper (Ho et al., 2020) grounded strictly in its own text: the forward process that adds noise and the reverse process that removes it, why the objective settles into 'predict the noise', how a simplified loss hurt likelihood while improving samples, and what the paper does and does not say about step count. 89 ·VLMs & Multimodal·FREE·PAPER·7 min read Paper Deep Dive — CLIP: Putting Words and Images on One Map A reading of the CLIP paper (Radford et al., 2021) grounded strictly in its own text: how the in-batch positives and negatives work, why zero-shot classification is really a hypernetwork trick, the five points that prompt wording is worth, and the long list of limits the authors wrote themselves. 90 ·Media in Production·★ MEMBER·9 min read Designing a Bitrate Ladder — The First Job You Get in Streaming Why one video needs several renditions. From how ABR works to rate-distortion curves per resolution and the convex hull that picks your rungs, the three ways excess bitrate costs you, how PSNR, SSIM and VMAF differ and which one decides, and per-title encoding — ending in a step-by-step procedure from choosing clips to keeping the ladder honest. 91 ·Video Codecs·FREE·8 min read Video Compression from Scratch — Motion Compensation and the GOP Compressing thirty separate photographs a second gets nowhere near today's delivery bitrates. Why frame differencing breaks, what a motion vector actually carries, I/P/B frames and the GOP, and what CBR, VBR and CRF each hold constant — ending at the keyframe interval a delivery engineer has to choose. 92 ·Image Codecs·FREE·8 min read Why PNG Does Not Degrade — Prediction Filters and Deflate What it means to shrink a file without changing a single bit. Starting from why no compressor can shrink everything, then PNG's five row filters as prediction-and-residual, Deflate (LZ77 plus Huffman), and why photographs resist it while screenshots collapse. Ending with a decision procedure for choosing between PNG and JPEG. 93 ·Image Codecs·★ MEMBER·9 min read Why JPEG Degrades — The DCT and Quantization from Scratch When a photo shrinks to a tenth of its size, what exactly was thrown away? Colour conversion, 8×8 blocks, the DCT, the quantization table and the zigzag scan — followed by what the number in "quality 90" really is, and where blocking and mosquito noise are born. Ending with the decisions people who ship images actually make. 94 ·CNNs & Image Recognition·FREE·8 min read Image Classification from Scratch — The Invention of the Convolution Feed a photograph straight into a fully connected layer and you get over a hundred million parameters — and a model for which the same cat, moved a few pixels, is an entirely different input. The convolution solves both with one idea: slide a small window. Kernels, stride, padding and pooling, ending with softmax turning scores into probabilities.