Tsinghua University

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

VoyageWang submitted a paper 2 days ago

Segment Anything with Motion, Geometry, and Semantic Adaptation for Complex Nonlinear Visual Object Tracking

long2333 submitted a paper 3 days ago

Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection

hansenhua submitted a paper 10 days ago

Learning to Explore: Scaling Agentic Reasoning via Exploration-Aware Policy Optimization

View all activity

Papers

Segment Anything with Motion, Geometry, and Semantic Adaptation for Complex Nonlinear Visual Object Tracking

Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection

View all Papers

Tsinghua 's Papers 36

Submitted by

Voyage_Wang

Segment Anything with Motion, Geometry, and Semantic Adaptation for Complex Nonlinear Visual Object Tracking

Tsinghua University

Submitted by

Guanglong Sun

Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection

Tsinghua University

Submitted by

Xingyuan Hua

Learning to Explore: Scaling Agentic Reasoning via Exploration-Aware Policy Optimization

Tsinghua University

Submitted by

Jintao Zhang

KernelBench-X: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels

Tsinghua University

Submitted by

Guohong Liu

Mobile GUI Agents under Real-world Threats: Are We There Yet?

Tsinghua University

Submitted by

Voyage_Wang

TAIHRI: Task-Aware 3D Human Keypoints Localization for Close-Range Human-Robot Interaction

Tsinghua University

Submitted by

jiacheng

Unleashing Spatial Reasoning in Multimodal Large Language Models via Textual Representation Guided Reasoning

Tsinghua University

2

Submitted by

Kai Li

BEAVER: A Training-Free Hierarchical Prompt Compression Method via Structure-Aware Page Selection

Tsinghua University

Submitted by

Jintao Zhang

6Bit-Diffusion: Inference-Time Mixed-Precision Quantization for Video Diffusion Models

Tsinghua University

2

Submitted by

Zi-Han Wang

CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges

Tsinghua University

Submitted by

Bingxiang He

How Far Can Unsupervised RLVR Scale LLM Training?

Tsinghua University

Submitted by

Wenbosi

IF-RewardBench: Benchmarking Judge Models for Instruction-Following Evaluation

Tsinghua University

Submitted by

You Li

Imagination Helps Visual Reasoning, But Not Yet in Latent Space

Tsinghua University

Submitted by

Jason Liu

JAEGER: Joint 3D Audio-Visual Grounding and Reasoning in Simulated Physical Environments

Tsinghua University

2

Submitted by

Voyage_Wang

Embed-RL: Reinforcement Learning for Reasoning-Driven Multimodal Embeddings

Tsinghua University

Submitted by

Jintao Zhang

SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning

Tsinghua University

6

Submitted by

Zhixuan Liang

BiManiBench: A Hierarchical Benchmark for Evaluating Bimanual Coordination of Multimodal Large Language Models

Tsinghua University

Submitted by

Jintao Zhang

Geometry-Aware Rotary Position Embedding for Consistent Video World Model

Tsinghua University

Submitted by

Xingyuan Hua

Context Learning for Multi-Agent Discussion

Tsinghua University

Submitted by

wenyan li

ExpAlign: Expectation-Guided Vision-Language Alignment for Open-Vocabulary Grounding

Tsinghua University

Submitted by

Rajkumar rawal

Continual GUI Agents

Tsinghua University

Collision-Free Humanoid Traversal in Cluttered Indoor Scenes

Tsinghua University

Submitted by

Shengjun Zhang

E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models

Tsinghua University

Submitted by

Bingxiang He

JustRL: Scaling a 1.5B LLM with a Simple RL Recipe

Tsinghua University

Submitted by

fansunqi

Tool-Augmented Spatiotemporal Reasoning for Streamlining Video Question Answering Task

Tsinghua University

Submitted by

kkaka

MIND-V: Hierarchical Video Generation for Long-Horizon Robotic Manipulation with RL-based Physical Alignment

Tsinghua University

Submitted by

kkaka

Controllable Layer Decomposition for Reversible Multi-Layer Image Generation

Tsinghua University

Submitted by

ZhenYang21

MathSE: Improving Multimodal Mathematical Reasoning via Self-Evolving Iterative Reflection and Reward-Guided Fine-Tuning

Tsinghua University

Submitted by

ZhenYang21

WebVIA: A Web-based Vision-Language Agentic Framework for Interactive and Verifiable UI-to-Code Generation

Tsinghua University

RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging

Tsinghua University

Submitted by

潘子豪

Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views

Tsinghua University

Submitted by

Xiaoji Zheng

CoIRL-AD: Collaborative-Competitive Imitation-Reinforcement Learning in Latent World Models for Autonomous Driving

Tsinghua University

Submitted by

Runze Liu

Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models

Tsinghua University

Submitted by

Jintao Zhang

SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention

Tsinghua University

Submitted by

Xiao Liang

Beyond the Exploration-Exploitation Trade-off: A Hidden State Approach for LLM Reasoning in RLVR

Tsinghua University

Submitted by

Kai Li

Efficient Audio-Visual Speech Separation with Discrete Lip Semantics and Multi-Scale Global-Local Attention

Tsinghua University