#reasoning

21 articles

01 ·Large Language Models·★ MEMBER·PAPER·8 min read Paper Explained: Bellman Policy Optimization — Policy Mirror Descent for LLMs, Without a Value Model In LLM reinforcement learning where only the final answer is scored, BPO (arXiv:2609.15987) targets the same optimum as Policy Mirror Descent without estimating a single intermediate state value. We walk from the Bellman 'telescoping sum' to the practical loss, using only the paper itself as the source. 02 ·Inference & Serving·★ MEMBER·PAPER·7 min read Paper Explained: When EOS Tokens Disagree — Why On-Policy Distillation Students Forget How to Stop In on-policy distillation, student responses can grow until they hit the generation budget. This paper (arXiv:2609.20511) traces a major cause to student and teacher marking 'the end' with different special tokens. We walk through it from scratch, using only the paper itself. 03 ·Inference & Serving·★ MEMBER·PAPER·8 min read Paper Explained: Negative Self-Distillation — Learning to Reason by Steering Away From Your Worst Self Self-distillation from ground-truth solutions (OPSD) can strip a reasoning model of its habit of pausing and double-checking. NSD has the model play a 'careless reasoner' and trains only to move away from that bad teacher — no labels required. A from-scratch walkthrough. 04 ·Inference & Serving·★ MEMBER·PAPER·7 min read Paper Explained: An Open Recipe for IMO Gold — How Open Models Reached Olympiad Gold with Generate, Verify, Refine NVIDIA's open recipe uses three Nemotron 3 Ultra checkpoints to generate, verify, and refine proofs, scoring 30/42 (gold-medal level) at IMO 2026. We explain it from scratch as a test-time-compute design. 05 ·Inference & Serving·★ MEMBER·PAPER·12 min read Paper walkthrough: BeaconKV — evicting KV cache by predicting when a reasoning model will re-read its own plan Deep into a long chain of thought, a reasoning model occasionally looks back at the plan it wrote at the start. The queries that do this cluster into a handful of groups in embedding space — so keeping a few dozen cluster representatives (beacons) is enough to predict which KV pairs will be revisited. A training-free method with up to 5.8× less memory and over 4.3× more throughput, read through its equations and code. 06 ·Large Language Models·★ MEMBER·PAPER·13 min read Paper Explained: FlowBalance — Verifier-Grounded Self-Improvement from a Model's Own Reasoning Learning from your own answers breaks in two ways: the grading is too sparse, or you believe your own confidence. FlowBalance fixes both with one move — let the verifier decide the sign of the dense self-score — and learns a normalized distribution over whole responses. Explained from first principles. 07 ·FREE·PAPER·9 min read Chain-of-Thought from Scratch — What Changes When You Make a Model Show Its Work Why does adding "think step by step" make a model solve problems it otherwise fails? A ground-up tour of few-shot CoT, zero-shot CoT and self-consistency — the serialization argument for why it works, the conditions where it doesn't, and how it relates to today's reasoning models. 08 ·FREE·PAPER·9 min read Chain-of-Thought from Scratch — What Changes When You Make a Model Show Its Work Why does adding "think step by step" make a model solve problems it otherwise fails? A ground-up tour of few-shot CoT, zero-shot CoT and self-consistency — the serialization argument for why it works, the conditions where it doesn't, and how it relates to today's reasoning models. 09 ·Inference & Serving·★ MEMBER·PAPER·12 min read Paper Walkthrough: Random Attention — Throwing KV Cache Entries Away at Random Works Just as Well The importance score that decides what leaves the KV cache turns out to buy almost nothing. Keep the prompt, evict uniformly at random inside each head, and you match the strongest prior evictor while serving 32-43% more tokens per second in vLLM. A walkthrough of the measurements across four models and six tasks, and the two controlled experiments that explain them. 10 ·Evaluation & Judging·★ MEMBER·PAPER·12 min read Self-Improving AI — Self-Play, Co-Evolution, and Generated Curricula What has to be true for a model to get better without anyone adding data? This article pulls three conditions out of AlphaZero's self-play, shows exactly which one breaks first for language models, explains how co-evolution and generated curricula try to patch the gap, and ends with why self-improvement claims are unusually easy to evaluate wrong. 11 ·Inference & Serving·★ MEMBER·PAPER·11 min read TTPO Explained: Training a Model Mid-Exam, With No Answer Key Majority-vote pseudo-labels are wrong on roughly 85% of competition math prompts. So why does training still work? A ground-up walkthrough of TTPO's asymmetric design: distill the rollouts that agree, penalize the ones that disagree. 12 ·Large Language Models·FREE·PAPER·13 min read Test-Time Scaling — How Models Get Better by Thinking Longer The same model scores higher when you let it think longer. This article builds the idea from scratch: chain-of-thought as purchased compute steps, self-consistency by majority vote, verifiers that pick the winner, and o1-style models that learned the thinking itself — and what it means for compute to shift from training to inference. 13 ·Large Language Models·FREE·PAPER·13 min read Test-Time Scaling — How Models Get Better by Thinking Longer The same model scores higher when you let it think longer. This article builds the idea from scratch: chain-of-thought as purchased compute steps, self-consistency by majority vote, verifiers that pick the winner, and o1-style models that learned the thinking itself — and what it means for compute to shift from training to inference. 14 ·Paper Deep-Dives·FREE·12 min read Symbolic vs. Connectionist — Where a 60-Year Argument Stands Today AI has always had two tribes: one that writes the rules down, one that learns weights from examples. Tracing the Perceptrons book, the collapse of expert systems, and the backpropagation comeback explains why today's LLMs still call calculators and get shackled to grammars. 15 ·Large Language Models·★ MEMBER·PAPER·11 min read Scaling Skepticism — A Genealogy of the "Just Make It Bigger" Critique A fair accounting of the case against "more parameters, more data" — data exhaustion, the reasoning wall, and the world-model dispute. The evidence for scaling gets the same scrutiny as the evidence against it, and every claim comes with the observation that would settle it. 16 ·Large Language Models·★ MEMBER·PAPER·11 min read Scaling Skepticism — A Genealogy of the "Just Make It Bigger" Critique A fair accounting of the case against "more parameters, more data" — data exhaustion, the reasoning wall, and the world-model dispute. The evidence for scaling gets the same scrutiny as the evidence against it, and every claim comes with the observation that would settle it. 17 ·Model Families·FREE·9 min read The DeepSeek Family from Scratch — Breaking In with MoE and Distillation DeepSeek redrew the open-LLM map with four tools: MoE, MLA, GRPO, and distillation. Walk the V2/V3/R1 lineage from zero prerequisites, learn how to read that famous training-cost number, and find out what the distilled models are actually for. 18 ·Inference & Serving·FREE·PAPER·14 min read Paper Walkthrough: No Gold Answers, No Stronger Teacher — How u-OPSD Distills From Its Own Majority Vote u-OPSD (arXiv:2608.06296) replaces the gold solution in on-policy self-distillation with the model's own majority vote, then corrects only the rollouts that disagree with it. A from-scratch walkthrough grounded solely in the paper. 19 ·Inference & Serving·FREE·PAPER·8 min read Paper Walkthrough: DAPD — Breaking the Teacher's "Cheat-Sheet Illusion" in Distillation with Dual Anchors When you distill from a teacher that can see the reference solution, the student learns to act as if invisible answers were still there — the privilege illusion. DAPD (arXiv:2608.01735) traces this failure to information asymmetry and fixes it with two levels of anchoring. A walkthrough grounded strictly in the paper itself. 20 ·Inference & Serving·FREE·PAPER·8 min read Paper explained: BDH-CQ — an AI that thinks without words. Recurrent memory plus latent reasoning resets ARC's cost frontier BDH-CQ (arXiv:2608.09888) never verbalizes its intermediate reasoning: demonstrations are written into a recurrent memory, and the answer is computed by iterating in a high-dimensional latent space. A 150M-parameter model reaches 29.5% pass@2 on ARC-AGI-1 at $0.0007 per task, breaking the reported cost–accuracy Pareto frontier. We explain the paper using only its own text as evidence. 21 ·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.