Yunxin Liu

LogicSR: A Unified Benchmark for Logical Discovery from Data

Sample Efficient Offline RL via T-Symmetry Enforced Latent State-Stitching

SMAN-Bench: A Cross-System Benchmark for Mobile Agents under Single- and Multi-path, Ambiguous, and Noisy Tasks

AdaNav: Adaptive Reasoning with Uncertainty for Vision-Language Navigation

BudgetThinker: Empowering Budget-aware LLM Reasoning with Control Tokens

AVI-Bench: Toward Human-like Audio-Visual Intelligence of Omni-MLLMs

Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management

Hijacking JARVIS: Benchmarking Mobile GUI Agents against Unprivileged Third Parties

Enhancing Agentic Textual Graph Retrieval with Synthetic Step-wise Supervision

ParaThinker: Native Parallel Thinking as a New Paradigm to Scale LLM Test-time Compute

AVSU-Bench and VSpeech-R1: A Dataset and MLLM for Audio-Visual Speech Understanding

Data Center Cooling System Optimization Using Offline Reinforcement Learning

Pushing the Limit of Small-Efficient Offline Reinforcement Learning

LoRA-Switch: Boosting the Efficiency of Dynamic LLM Adapters via System-Algorithm Co-design

Preserving Large Activations: The Key to KV Cache Pruning