Papers

Fast-dLLM v2: Efficient Block-Diffusion LLM

Less is More: Recursive Reasoning with Tiny Networks

Fathom-DeepResearch: Unlocking Long Horizon Information Retrieval and Synthesis for SLMs

TaTToo: Tool-Grounded Thinking PRM for Test-Time Scaling in Tabular Reasoning

Hybrid Architectures for Language Models: Systematic Analysis and Design Insights

MITS: Enhanced Tree Search Reasoning for LLMs via Pointwise Mutual Information

Imperceptible Jailbreaking against Large Language Models

VChain: Chain-of-Visual-Thought for Reasoning in Video Generation

Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models

Paper2Video: Automatic Video Generation from Scientific Papers

Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization

Self-Improvement in Multimodal Large Language Models: A Survey

Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition

Large Reasoning Models Learn Better Alignment from Flawed Thinking

Efficient Multi-modal Large Language Models via Progressive Consistency Distillation

Apriel-1.5-15b-Thinker

StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets?

Interactive Training: Feedback-Driven Neural Network Optimization

StealthAttack: Robust 3D Gaussian Splatting Poisoning via Density-Guided Illusions

ExGRPO: Learning to Reason from Experience

Self-Forcing++: Towards Minute-Scale High-Quality Video Generation

LongCodeZip: Compress Long Context for Code Language Models

PIPer: On-Device Environment Setup via Online Reinforcement Learning

Rethinking Reward Models for Multi-Domain Test-Time Scaling

Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation

GEM: A Gym for Agentic LLMs

VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators

DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search