Blog
No more endless PDFs. Discover the core value of the latest top-tier research in one article.
How to Allocate Your Tokens? Scaling Laws with Training Steps and Batch Size
Program-as-Weights: A Programming Paradigm for Fuzzy Functions
The Flexibility Trap: Rethinking the Value of Arbitrary Order in Diffusion Language Models
Position: The Alignment Community is Unintentionally Building a Censor's Toolkit
High-accuracy sampling for diffusion models and log-concave distributions
The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes
Motion Attribution for Video Generation
To Grok Grokking: Provable Grokking in Ridge Regression
A Random Matrix Theory Perspective on the Consistency of Diffusion Models
Position: AI/ML Deepfake Research is Misaligned with AI-Generated Non-Consensual Intimate Imagery (AIG-NCII)
Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning
Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity
TREK: Distill to Explore, Reinforce to Refine
Vision Pretraining for Dense Spatial Perception
TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training
LLM-as-a-Verifier: A General-Purpose Verification Framework
From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning
Trees from Marginals: Autoregressive drafting with factorized priors
Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents
LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL
A Random Matrix Theory Perspective on the Consistency of Diffusion Models
Scalable Visual Pretraining for Language Intelligence
The State-Prediction Separation Hypothesis
Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading
Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Data
Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning
Metacognition in LLMs: Foundations, Progress, and Opportunities
Domain-aware scaling laws uncover data synergy
Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers