2 citations · 2 across the 15 of their papers we have counts for
18 papers
Asking Less, Adapting Better: Feedback-Efficient Test-Time Adaptation for Vision-and-Language Navigation
Zixu Wang, Huaquan Zhang, Shoukai Xu +3
Vision-and-Language Navigation (VLN) requires agents to follow instructions and navigate to target locations. However, current VLN agents often suffer severe performance degradatio…
A Survey on Self-Improving Test-Time Intelligence: Feedback-Driven Adapting, Learning, and Scaling at Inference
Shuaicheng Niu, Guohao Chen, Yaofo Chen +14
The ability of AI systems to improve their behavior during deployment is becoming increasingly important. As inference moves beyond the static execution of a fixed trained model, a…
Preference-Driven Online Adaptation for Personalized Interaction Initiation in Proactive AI Assistants
Yufeng Wang, Wei Zhang, Zhiquan Wen +5
AI assistants are typically reactive, relying on users to initiate interactions. Proactive assistants go beyond this paradigm by autonomously initiating interactions based on users…
Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders
Yi Jing, Zao Dai, Jinwu Hu +4
Model internals encode rich information about how a large language model (LLM) processes its training data; however, post-training data engineering largely relies on external signa…
Instance-level Visual Active Tracking with Occlusion-Aware Planning
Haowei Sun, Kai Zhou, Hao Gao +5
Visual Active Tracking (VAT) aims to control cameras to follow a target in 3D space, which is critical for applications like drone navigation and security surveillance. However, it…
Training-Free Test-Time Contrastive Learning for Large Language Models
Kaiwen Zheng, Kai Zhou, Jinwu Hu +3
Large language models (LLMs) demonstrate strong reasoning capabilities, but their performance often degrades under distribution shift. Existing test-time adaptation (TTA) methods r…
Precedent-Informed Reasoning: Mitigating Overthinking in Large Reasoning Models via Test-Time Precedent Learning
Qianyue Wang, Jinwu Hu, Huanxiang Lin +5
Reasoning in Large Language Models (LLMs) often suffers from inefficient long chain-of-thought traces with redundant self-exploration and validation, which inflate computational co…
Beyond Fast and Slow: Cognitive-Inspired Elastic Reasoning for Large Language Models
Jinwu Hu, Dongjin Yang, Langyu Bian +6
Large language models (LLMs) have demonstrated impressive performance across various language tasks. However, existing LLM reasoning strategies mainly rely on the LLM itself with f…
Beyond Model Scaling: Test-Time Intervention for Efficient Deep Reasoning
Qianyue Wang, Jinwu Hu, Yufeng Wang +5
Large Reasoning Models (LRMs) excel at multi-step reasoning but often suffer from inefficient reasoning processes like overthinking and overshoot, where excessive or misdirected re…
EvidFuse: Writing-Time Evidence Learning for Consistent Text-Chart Data Reporting
Huanxiang Lin, Qianyue Wang, Jinwu Hu +3
Data-driven reports communicate decision-relevant insights by tightly interleaving narrative text with charts grounded in underlying tables. However, current LLM-based systems typi…
Continual Knowledge Adaptation for Reinforcement Learning
Jinwu Hu, Zihao Lian, Zhiquan Wen +5
Reinforcement Learning enables agents to learn optimal behaviors through interactions with environments. However, real-world environments are typically non-stationary, requiring ag…
Zero-Shot Skeleton-Based Action Recognition With Prototype-Guided Feature Alignment
Kai Zhou, Shuhai Zhang, Zeng You +3
Zero-shot skeleton-based action recognition aims to classify unseen skeleton-based human actions without prior exposure to such categories during training. This task is extremely c…
Enhancing User-Oriented Proactivity in Open-Domain Dialogues with Critic Guidance
Yufeng Wang, Jinwu Hu, Ziteng Huang +10
Open-domain dialogue systems aim to generate natural and engaging conversations, providing significant practical value in real applications such as social robotics and personal ass…
Dynamic Compressing Prompts for Efficient Inference of Large Language Models
Jinwu Hu, Wei Zhang, Yufeng Wang +4
Large Language Models (LLMs) have shown outstanding performance across a variety of tasks, partly due to advanced prompting techniques. However, these techniques often require leng…
Generating Long-form Story Using Dynamic Hierarchical Outlining with Memory-Enhancement
Qianyue Wang, Jinwu Hu, Zhengping Li +4
Long-form story generation task aims to produce coherent and sufficiently lengthy text, essential for applications such as novel writingand interactive storytelling. However, exist…
Enhancing Perception Capabilities of Multimodal LLMs with Training-Free Fusion
Zhuokun Chen, Jinwu Hu, Zeshuai Deng +3
Multimodal LLMs (MLLMs) equip language models with visual capabilities by aligning vision encoders with language models. Existing methods to enhance the visual perception of MLLMs…
Efficient Dynamic Ensembling for Multiple LLM Experts
Jinwu Hu, Yufeng Wang, Shuhai Zhang +5
LLMs have demonstrated impressive performance across various language tasks. However, the strengths of LLMs can vary due to different architectures, model sizes, areas of training…
Open-World Drone Active Tracking with Goal-Centered Rewards
Haowei Sun, Jinwu Hu, Zhirui Zhang +7
Drone Visual Active Tracking aims to autonomously follow a target object by controlling the motion system based on visual observations, providing a more practical solution for effe…