Shizhe Diao

Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding

GAR: Generative Adversarial Reinforcement Learning for Formal Theorem Proving

ProfBench: Multi-Domain Rubrics requiring Professional Knowledge to Answer and Judge

Fast-dLLM v2: Efficient Block-Diffusion LLM

ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration

LaTtE-Flow: Layerwise Timestep-Expert Flow-based Transformer

DLER: Doing Length pEnalty Right — Incentivizing More Intelligence per Token via Reinforcement Learning

Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed

Generalizable Geometric Image Caption Synthesis

BroRL: Scaling Reinforcement Learning via Broadened Exploration

Double-Checker: Enhancing Reasoning of Slow-Thinking LLMs via Self-Critical Fine-Tuning

TinyEye: Sharpening Visual Reasoning of Tiny Models with Offline Policy Optimization

Federated Agent Reinforcement Learning

AgentHard: Hardening LLM-Agent Evaluation with a Taxonomy of Artifacts and Automated Cleaning

GPAS: Accelerating Convergence of LLM Pretraining via Gradient-Preserving Activation Scaling

Hymba: A Hybrid-head Architecture for Small Language Models

ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models

Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models

LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement

UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language Models

Double-Checker: Enhancing Reasoning of Slow-Thinking LLMs via Self-Critical Fine-Tuning

$PLUM$: Improving Code LMs Using On-Policy Preference Learning Powered by Automatic Test Cases

LLM Pruning and Distillation in Practice

MA-LoT: Model-Collaboration Lean-based Long Chain-of-Thought Reasoning enhances Formal Theorem Proving

Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models