Analyzed Papers
Research papers analyzed and organized by topic
W9: Memory, Compression and Representation Learning (Part 2)
W10: Complexity & Theoretical Physics Cross-over
W12: Frontiers & Alignment (Part 1)
W13: Frontiers & Alignment (Part 2)
W14: Hierarchical Reasoning Models
W15: SOTA Open-Weight Reasoning LLM + Frontier Risks
W17: Text / Language Diffusion
W18: Text / Language Diffusion (Cont.)
W28: Sample Size Consistency in LLM Poisoning
W29: Nested Learning: The Illusion of Deep Learning Architectures
W30: Modern OCR: Efficient Recognition in the LLM Era
W31: LLM-based Evolutionary Code Agent for Mathematics and Algorithmic Discovery
W38: Execution-Grounded AI Research
W39: Agentic Operator Generation for ML ASICs
W40: Strategist - Self-improvement of LLM Decision Making via Bi-Level Tree Search
W41: Direct Preference Optimization (DPO): Your Language Model is Secretly a Reward Model
W42: Self-Distillation Enables Continual Learning
W43: On-Policy Self-Distillation for Reasoning Compression
W44: Goedel-Prover: Frontier Models for Automated Theorem Proving
W45: Attention Residuals: Rethinking Information Flow in LLMs
W46: AutoHarness: Improving LLM Agents by Automatically Synthesizing a Code Harness
W47: TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate
W48: Inside vLLM: Anatomy of a High-Throughput LLM Inference System