works on

From the 1 of 31 linked papers with an AI index.

activity
20242026
collaborators

31 papers

quant-ph2026

Controlling quantum transport by measurement-rate modulation

Jesús Casado-Pascual, Luis Octavio Castaños-Cervantes

Temporal modulation of the measurement rate provides a powerful mechanism for controlling open-system dynamics through measurement backaction. We demonstrate this mechanism in a mi…

cs.LG2026

SMOPD: Multi-Reward Reinforcement Learning via Specialize-and-Merge Online Policy Distillation

Wen Wang, Jiahua Bao, Tu Yongsiqi +8

We aim to improve model performance in multi-reward reinforcement learning training process. Existing Group reward-Decoupled Normalization Policy Optimization (GDPO) has mitigated…

cs.MM2026

AcoustiTrace: When Plausible Sound Violates Physics

Shiyang Li, Yuewen Cao, Yihao Liu +4

Recent audio-video generators can produce semantically plausible and apparently synchronized sound, yet may still violate the acoustic processes implied by visible events and envir…

cs.CV2026

See2Think: Do Multimodal Models Really Use Intermediate Visual States?

Siyu Yan, Zhuoran Yan, Haiying Xu +10

The paper presents See2Think, an evaluation framework and benchmark for testing whether multimodal large language models actually use intermediate visual states during reasoning, a…

cs.CL2026

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills

Siyuan Huang, Pengyu Cheng, Haotian Liu +10

LLM training is shifting from manual design and annotation to interaction-driven self-evolution. However, existing self-evolutionary methods face a fundamental dilemma between task…

cs.AI2026

From Passive Retrieval to Active Memory Navigation: Learning to Use Memory as a Structured Action Space

Yue Xu, Yutao Sun, Yihao Liu +7

Long-term user memory is essential for personalized conversational agents, yet many memory systems still expose memory through passive retrieval interfaces, making the model a cons…