Publications

Oct 25, 2026
Recycler: Cost-Free Latent Reasoning via Hidden State Recycling
Oct 15, 2026
Full-Duplex Interaction with Speech, Expressions and Gestures
Oct 14, 2026
Cortex: Consolidating Context into Parametric Memory
Oct 11, 2026
ObsSpec: Accelerating Agentic Reinforcement Learning with Observation Speculation
Oct 8, 2026
One Model, Multiple Compute Budgets: Multi-Ratio ConceptMoE for Flexible Compute Across Turns
Oct 1, 2026
FastCI: Efficient GPU-Intensive CI for LLM Training Frameworks
Sep 28, 2026
Periodic Weak Spots: Phase Sensitivity from Chunked KV-Cache Compression
Sep 25, 2026
Block Sparse Attention with Log-Linear Complexity
Sep 25, 2026
Aligning One-Step Generative Models with Reward-Weighted Transport Distillation
Sep 23, 2026
EmbodiedSWE: Coding Agents for Long Horizon Dexterous Robotics
Sep 19, 2026
NSP: Accelerating Variable-Length LLM Training via Nested Sequence Parallelism
Sep 19, 2026
Towards Full Pipeline FP8 Reinforcement Learning for LLMs
Sep 1, 2026
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?
Aug 31, 2026
S³Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?
Aug 31, 2026
Aspire: Can Models Self-Evolve from Vague Goals?
Aug 26, 2026
Unfolding Scientific Papers into Multi-Turn Generation Trajectories for Continued Pre-Training
Aug 18, 2026
Chain-of-Experience for Continual LLM Improvement
Aug 12, 2026
Harness-IF: Evaluating Instruction Following Across Instruction Surfaces in Coding Agents
Aug 6, 2026
GST-Bench: Can VLMs Develop Global Spatial Awareness from Video?
1-20 of 278
Page 1 of 14