Research Papers Institution
Leading Chinese research university; its AI groups drive work in deep generative models, diffusion, and machine learning.
Efficient AI · Tsinghua University
SD3.5-T5 swaps Softmax attention for a Test-Time-Training layer that inherits pretrained Q/K/V/O weights, hitting GenEval 0.69 (vs 0.70 fine-tuned Softmax) after 3000 steps and running 1.32x faster at 1K, 1.47x at 2K.
Vision-Language-Action · ACE Robotics
ACE-Ego-0 pretrains a VLA on 6,000+ hours mixing robot trajectories with human egocentric video turned into pseudo-actions. It averages 78.3% on six real bimanual tasks vs 71.7% for pi-0.5 and 35.6% for GR00T-N1.7.
AI Agents · The Chinese University of Hong Kong
Orchestra-o1 orchestrates text, image, audio, and video sub-agents and hits 72.8% on OmniGAIA with a GPT-5 brain (+10.3 over Gemini-3-Pro). Its trained 8B orchestrator reaches 30.0%, best among open omnimodal agents.
A Tencent YouTu Lab survey maps the chatbot-to-agent shift on two axes: cognitive core (Chatbot then Thinking LLM) and task execution (Agent then Workspace plus Skill), arguing persistent state is the real leap.
SCAIL-2 feeds the raw driving video into the generation sequence instead of a pose skeleton, cutting FVD to 287 vs 305 for Wan-Animate on Studio-Bench, with one model covering animation and replacement.
SearchSwarm fine-tunes Tongyi DeepResearch-30B-A3B on harness-generated delegation trajectories, lifting BrowseComp from 43.4 to 68.1 and topping every 30B-A3B model on four deep-research benchmarks.
Video Generation · Tsinghua University
OmniDirector copies camera motion from a reference video into new generations and cuts rotation error to 2.64 degrees, beating CamCloneMaster (4.11), with no cross-paired training data.
AI Agents · Tsinghua University
EurekAgent argues the bottleneck is agent environment design, reporting 2.635999 on 26-circle packing, 2005.03 us TriMul, and 85.71% any-medal on a seven-task MLE-Bench subset.
AI Agents · Zhejiang University
WeaveBench tests 114 real hybrid GUI plus CLI tasks; the best frontier pairing reaches only 41.2% PassRate, and final-only grading overstates GPT-5.5 by 20.2 points.
MaxProof turns MiniMax-M3 into a generator, verifier, fixer, and ranker; with population-level test-time scaling it reports 35/42 on IMO 2025 and 36/42 on USAMO 2026.
Long Context · Tsinghua University
Tsinghua's LongTraceRL mines distractors from real search-agent trajectories and adds entity-level rubric rewards, lifting a Qwen3-4B reasoner from 53.3 to 59.0 average across five long-context benchmarks (+5.7).
Reinforcement Learning · Tsinghua University
CHERRL injects four known judge biases to reliably reproduce reward hacking in rubric RL; an agent reading only training logs pinned the onset with 11-step total interval error and missed none of six runs.
Echo-Infinity is an autoregressive video model with a learnable evolving memory that compresses any-length history at constant cost, hitting 24-hour rollouts (over 1.3M frames) in real time at 18.5 FPS on an H100.
Robotics · Tsinghua University
Humanoid-GPT treats humanoid control like language modeling: a causal Transformer distilled from ~384 PPO experts on a 2-billion-frame corpus, 200x prior data. It hits 92.58 percent sim success, under 1.5ms.
Diffusion Models · Tsinghua University
Causal Forcing++ distills bidirectional video diffusion into a 1-2 step frame-wise autoregressive generator at 14.1 FPS, halves first-frame latency, and cuts few-step training cost ~4x (11,600 to 2,900 A800 GPU hours).