2 citations · 2 across the 10 of their papers we have counts for
12 papers
Fine-Grained Activation Steering: Steering Less, Achieving More
Zijian Feng, Tianjiao Li, Zixiao Zhu +7
Activation steering has emerged as a cost-effective paradigm for modifying large language model (LLM) behaviors. Existing methods typically intervene at the block level, steering t…
Scaling Medical Reasoning Verification via Tool-Integrated Reinforcement Learning
Hang Zhang, Ruheng Wang, Yuelyu Ji +7
Large language models have achieved strong performance on medical reasoning benchmarks, yet their deployment in clinical settings demands rigorous verification to ensure factual ac…
Where on Earth? A Vision-Language Benchmark for Probing Model Geolocation Skills Across Scales
Zhaofang Qian, Hardy Chen, Zeyu Wang +9
Vision-language models (VLMs) have advanced rapidly, yet their capacity for image-grounded geolocation in open-world conditions, a task that is challenging and of demand in real li…
Prototype-Based Dynamic Steering for Large Language Models
Ceyhun Efe Kayan, Li Zhang
Despite impressive breadth, LLMs still rely on explicit reasoning instructions or static, one-fits-all steering methods, leaving a gap for adaptive, instruction-free reasoning ampl…
Documentation Retrieval Improves Planning Language Generation
Renxiang Wang, Li Zhang
Certain strong LLMs have shown promise for zero-shot formal planning by generating planning languages like PDDL. Yet, the performance of most open-source models under 50B parameter…
GOSU: Retrieval-Augmented Generation with Global-Level Optimized Semantic Unit-Centric Framework
Xuecheng Zou, Ke Liu, Bingbing Wang +3
Building upon the standard graph-based Retrieval-Augmented Generation (RAG), the introduction of heterogeneous graphs and hypergraphs aims to enrich retrieval and generation by lev…
Rethinking Layered Graphic Design Generation with a Top-Down Approach
Jingye Chen, Zhaowen Wang, Nanxuan Zhao +4
Graphic design is crucial for conveying ideas and messages. Designers usually organize their work into objects, backgrounds, and vectorized text layers to simplify editing. However…
Cross from Left to Right Brain: Adaptive Text Dreamer for Vision-and-Language Navigation
Pingrui Zhang, Yifei Su, Pengyuan Wu +7
Vision-and-Language Navigation (VLN) requires the agent to navigate by following natural instructions under partial observability, making it difficult to align perception with lang…
Iterative Formalization and Planning in Partially Observable Environments
Liancheng Gong, Wang Zhu, Jesse Thomason +1
Using LLMs not to predict plans but to formalize an environment into the Planning Domain Definition Language (PDDL) has been shown to improve performance and control. While most ex…
Not that Groove: Zero-Shot Symbolic Music Editing
Li Zhang
While recent advancements in AI music generation have predominantly focused on direct audio synthesis, these systems suffer from inherent rigidity, limiting their utility for profe…
Structured Event Reasoning with Large Language Models
Li Zhang
Reasoning about real-life events is a unifying challenge in AI and NLP that has profound utility in a variety of domains, while fallacy in high-stake applications could be catastro…
Complementary Evidence Identification in Open-Domain Question Answering
Xiangyang Mou, Mo Yu, Shiyu Chang +3
This paper proposes a new problem of complementary evidence identification for open-domain question answering (QA). The problem aims to efficiently find a small set of passages tha…