2 citations · 4 across the 12 of their papers we have counts for
14 papers
MemLife: Curating and Reasoning over Long-Term Egocentric Video Memories
Guangzhi Xiong, Xinyuan Zhang, Xiao Yang +14
Long-term egocentric video enables personalized AI assistants to reason about daily life. However, as video histories grow to hundreds of hours spanning months or years, reprocessi…
SaliMory: Orchestrating Cognitive Memory for Conversational Agents
Kai Zhang, Xinyuan Zhang, Hongda Jiang +11
Conversational agents that serve as lifelong companions must maintain persistent memory across all interactions. However, simply expanding context windows with raw retrieval degrad…
Ask a Strong LLM Judge when Your Reward Model is Uncertain
Zhenghao Xu, Qin Lu, Qingru Zhang +9
Reward model (RM) plays a pivotal role in reinforcement learning with human feedback (RLHF) for aligning large language models (LLMs). However, classical RMs trained on human prefe…
Improving Sampling Efficiency in RLVR through Adaptive Rollout and Response Reuse
Yuheng Zhang, Wenlin Yao, Changlong Yu +5
Large language models (LLMs) have achieved impressive reasoning performance, with reinforcement learning with verifiable rewards (RLVR) emerging as a standard paradigm for post-tra…
SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs
Jiacheng Lin, Zhongruo Wang, Kun Qian +14
Supervised Fine-Tuning (SFT) on domain-specific datasets is a common approach to adapt Large Language Models (LLMs) to specialized tasks but is often believed to degrade their gene…
Many-Turn Jailbreaking
Xianjun Yang, Liqiang Xiao, Shiyang Li +5
Current jailbreaking work on large language models (LLMs) aims to elicit unsafe outputs from given prompts. However, it only focuses on single-turn jailbreaking targeting one speci…
Aligning Large Language Models with Implicit Preferences from User-Generated Content
Zhaoxuan Tan, Zheng Li, Tianyi Liu +10
Learning from preference feedback is essential for aligning large language models (LLMs) with human values and improving the quality of generated responses. However, existing prefe…
AutoMixAlign: Adaptive Data Mixing for Multi-Task Preference Optimization in LLMs
Nicholas E. Corrado, Julian Katz-Samuels, Adithya Devraj +6
When aligning large language models (LLMs), their performance on various tasks (such as being helpful, harmless, and honest) depends heavily on the composition of their training da…
WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning
Zhepei Wei, Wenlin Yao, Yao Liu +9
While reinforcement learning (RL) has demonstrated remarkable success in enhancing large language models (LLMs), it has primarily focused on single-turn tasks such as solving math…
RealWebAssist: A Benchmark for Long-Horizon Web Assistance with Real-World Users
Suyu Ye, Haojun Shi, Darren Shih +3
To achieve successful assistance with long-horizon web-based tasks, AI agents must be able to sequentially follow real-world user instructions over a long period. Unlike existing w…
Evolutionary Contrastive Distillation for Language Model Alignment
Julian Katz-Samuels, Zheng Li, Hyokun Yun +5
The ability of large language models (LLMs) to execute complex instructions is essential for their real-world applications. However, several recent studies indicate that LLMs strug…
Exposing Privacy Gaps: Membership Inference Attack on Preference Data for LLM Alignment
Qizhang Feng, Siva Rajesh Kasa, Santhosh Kumar Kasa +3
Large Language Models (LLMs) have seen widespread adoption due to their remarkable natural language capabilities. However, when deploying them in real-world settings, it is importa…
ESG Classification by Implicit Rule Learning via GPT-4
Hyo Jeong Yun, Chanyoung Kim, Moonjeong Hahm +2
Environmental, social, and governance (ESG) factors are widely adopted as higher investment return indicators. Accordingly, ongoing efforts are being made to automate ESG evaluatio…
Robust Multi-Task Learning with Excess Risks
Yifei He, Shiji Zhou, Guojun Zhang +5
Multi-task learning (MTL) considers learning a joint model for multiple tasks by optimizing a convex combination of all task losses. To solve the optimization problem, existing met…