3 citations · 5 across the 15 of their papers we have counts for
16 papers
Persistent Context Graphs for Efficient Memory Compaction in LLM Agents
Jingbo Yang, Kwei-Herng Lai, Xiaowen Wang +6
As LLM capabilities advance, agents are tackling increasingly complex tasks over longer horizons. Their growing interaction histories make memory compaction essential for staying w…
Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks
Nobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu +1
With the growing adoption of VLMs, DMs, LLMs, and AFMs, these multimodal foundation models can inadvertently encode sensitive, copyrighted, biased, or unsafe cross-modal associatio…
Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions
Diancheng Kang, Zheyuan Liu, Ningshan Ma +3
Activation steering controls language model behavior by adding directions to internal representations at inference time, but standard residual-stream steering can fail in stateful…
Bridging Textual Profiles and Latent User Embeddings for Personalization
Zhaoxuan Tan, Xiang Zhai, Yan Zhu +2
Personalized systems rely on user representations to connect behavioral history with downstream recommendation applications. Existing methods typically employ either supervised lat…
MTMCS-Bench: Evaluating Contextual Safety of Multimodal Large Language Models in Multi-Turn Dialogues
Zheyuan Liu, Dongwhi Kim, Yixin Wan +4
Multimodal large language models (MLLMs) are increasingly deployed as assistants that interact through text and images, making it crucial to evaluate contextual safety when risk de…
DRIFT: Learning from Abundant User Dissatisfaction in Real-World Preference Learning
Yifan Wang, Bolian Li, Junlin Wu +5
Real-world large language model deployments (e.g., conversational AI systems, code generation assistants) naturally generate abundant implicit user dissatisfaction (DSAT) signals,…
From Personal to Collective: On the Role of Local and Global Memory in LLM Personalization
Zehong Wang, Junlin Wu, ZHaoxuan Tan +4
Large language model (LLM) personalization aims to tailor model behavior to individual users based on their historical interactions. However, its effectiveness is often hindered by…
Steering Multimodal Large Language Models Decoding for Context-Aware Safety
Zheyuan Liu, Zhangchen Xu, Guangyao Dou +4
Multimodal Large Language Models (MLLMs) are increasingly deployed in real-world applications, yet their ability to make context-aware safety decisions remains limited. Existing me…
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…
IHEval: Evaluating Language Models on Following the Instruction Hierarchy
Zhihan Zhang, Shiyang Li, Zixuan Zhang +11
The instruction hierarchy, which establishes a priority order from system messages to user messages, conversation history, and tool outputs, is essential for ensuring consistent an…
Modality-Aware Neuron Pruning for Unlearning in Multimodal Large Language Models
Zheyuan Liu, Guangyao Dou, Xiangchi Yuan +3
Generative models such as Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) trained on massive datasets can lead them to memorize and inadvertently reveal s…
Enhancing Mathematical Reasoning in LLMs by Stepwise Correction
Zhenyu Wu, Qingkai Zeng, Zhihan Zhang +3
Best-of-N decoding methods instruct large language models (LLMs) to generate multiple solutions, score each using a scoring function, and select the highest scored as the final ans…
Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench
Zheyuan Liu, Guangyao Dou, Mengzhao Jia +4
Generative models such as Large Language Models (LLM) and Multimodal Large Language models (MLLMs) trained on massive web corpora can memorize and disclose individuals' confidentia…
CodeTaxo: Enhancing Taxonomy Expansion with Limited Examples via Code Language Prompts
Qingkai Zeng, Yuyang Bai, Zhaoxuan Tan +3
Taxonomies play a crucial role in various applications by providing a structural representation of knowledge. The task of taxonomy expansion involves integrating emerging concepts…
Empirical Guidelines for Deploying LLMs onto Resource-constrained Edge Devices
Ruiyang Qin, Dancheng Liu, Chenhui Xu +9
The scaling laws have become the de facto guidelines for designing large language models (LLMs), but they were studied under the assumption of unlimited computing resources for bot…
Large Language Models Can Self-Correct with Key Condition Verification
Zhenyu Wu, Qingkai Zeng, Zhihan Zhang +3
Intrinsic self-correct was a method that instructed large language models (LLMs) to verify and correct their responses without external feedback. Unfortunately, the study concluded…