13 citations · 35 across the 32 of their papers we have counts for
7 papers · 1 filter
Cavity-tunable Pseudospin-Hall Topology and Edge Transport
Minghui Niu, Yan Meng, Chengle Fan +5
Topological edge states are a hallmark of topological phases, with their existence tied to bulk band topology through bulk-edge correspondence. In photonic pseudospin-Hall systems,…
SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles
Yuyao Ge, Yiwei Wang, Yuchen He +5
Memory-augmented reinforcement learning strengthens LLM agents' ability to solve complex long-horizon tasks. Skills are one such form of memory, pairing instructions with an applic…
Omni-Decision: Evidence-Ledger Planning for Omni-Modal Agents
Ming Ma, Yi Zhu, Yiran Zhong +7
Omni-modal agents must seek evidence across video, audio, web pages, and computation to answer questions. Their main bottleneck is planning: noisy multimodal observations accumulat…
Multimodal Reward Hacking in Reinforcement Learning
Jiayu Yao, Yiwei Wang, Anmeng Zhang +5
Reinforcement learning (RL) is increasingly used to align multimodal large language models (MLLMs), but higher rewards do not always imply better task performance. This risk is amp…
PRISM-: Differential Subspace Steering for Prompt Highlighting in Large Language Models
Yuyao Ge, Shenghua Liu, Yiwei Wang +5
Prompt highlighting steers a large language model to prioritize user-specified text spans during generation. A key challenge of existing Key-editing approaches is extracting steeri…
PromptCD: Test-Time Behavior Enhancement via Polarity-Prompt Contrastive Decoding
Baolong Bi, Yuyao Ge, Shenghua Liu +9
Reliable AI systems require large language models (LLMs) to exhibit behaviors aligned with human preferences and values. However, most existing alignment approaches operate at trai…
Gated Differentiable Working Memory for Long-Context Language Modeling
Lingrui Mei, Shenghua Liu, Yiwei Wang +7
Long contexts challenge transformers: attention scores dilute across thousands of tokens, critical information is often lost in the middle, and models struggle to adapt to novel pa…