10 papers
ADAPT for Science: A Multi-Agent System for Self-Evolving Scientific Optimization
Zhaoran Feng, Yuchen Ni, Jianan Liu +3
Scientific discovery often requires identifying a small number of high-performing designs in vast, constrained search spaces. This is difficult when evaluations are costly, feasibl…
Nullify: Null-Space Activation Steering for Training-Free LLM Unlearning
Wei Zhai, Xiang Liu, Qiang Huang +6
Large Language Models (LLMs) inevitably internalize substantial amounts of sensitive or private information during pre-training, while LLM unlearning aims to selectively erase spec…
PGPO: Potential-Guided Policy Optimization for Multi-Turn Agentic Tasks
Yuyao Zheng, Haipeng Sun, Junwei Bao +4
Group-based reinforcement learning (RL) has become an effective paradigm for LLM post-training, but in multi-turn agentic tasks with sparse terminal rewards, it often provides coar…
SLIM-0.5B: Learning Action-Grounded Predictive Latents for Robot Manipulation
Jingkai Wang, Zihan Tang, Gu Zhang +7
Vision-language-action policies rely on large multimodal backbones to jointly perform perception, language conditioning, and action generation at every control step. Much of this c…
PAMNet: Cycle-aware Phase-Amplitude Modulation Network for Multivariate Time Series Forecasting
Yingbo Zhou, Yutong Ye, Zhiwei Ling +5
Reliable periodic patterns serve as a fundamental basis for accurate multivariate time series forecasting. However, existing methods either implicitly extract periodicity through c…
PAMod: Modeling Cyclical Shifts via Phase-Amplitude Modulation for Non-stationary Time Series Forecasting
Yingbo Zhou, Yutong Ye, Shuhao Li +5
Real-world time series forecasting faces the fundamental challenge of non-stationary statistical properties, including shifts in mean and variance over time. While reversible insta…
AnchorSeg: Language Grounded Query Banks for Reasoning Segmentation
Rui Qian, Chuanhang Deng, Qiang Huang +6
Reasoning segmentation requires models to ground complex, implicit textual queries into precise pixel-level masks. Existing approaches rely on a single segmentation token $\texttt{…
Unrewarded Exploration in Large Language Models Reveals Latent Learning from Psychology
Jian Xiong, Jingbo Zhou, Zihan Zhou +6
Latent learning, classically theorized by Tolman, shows that biological agents (e.g., rats) can acquire internal representations of their environment without rewards, enabling rapi…
UGround: Towards Unified Visual Grounding with Unrolled Transformers
Rui Qian, Xin Yin, Chuanhang Deng +4
We present UGround, a \textbf{U}nified visual \textbf{Ground}ing paradigm that dynamically selects intermediate layers across \textbf{U}nrolled transformers as ``mask as prompt,''…
Reasoning to Attend: Try to Understand How <SEG> Token Works
Rui Qian, Xin Yin, Dejing Dou
Current Large Multimodal Models (LMMs) empowered visual grounding typically rely on tokens as a text prompt to jointly optimize the vision-language model (e.g., LL…