3 citations · 25 across the 55 of their papers we have counts for
64 papers
Defending Against Dormant Poisoning Attacks Across Language and Multimodal Agents
Wonjun Lee, Vaidehi Patil, Zaid Khan +4
Recent work shows that attackers can implant dormant malicious behaviors that remain hidden at release but emerge after benign fine-tuning. As foundation models are used as agents,…
Who Should We Listen to More? Welfare-Aware Preference Acquisition for Pluralistic Alignment
Ruomeng Ding, Tianwei Gao, Lianrui Geng +2
Pluralistic alignment needs to accommodate diverse preferences under limited human feedback. Using AI simulators to label preference comparisons reduces annotation costs, but varia…
VEPA: Verified Evolving Formal Policy for Lifelong LLM Agent Guardrails
Duy Nguyen, Lesly Miculicich, Bhavana Dalvi Mishra +5
LLM agents increasingly operate over sensitive resources, such as private documents and mutable system states, which can create serious safety and security risks. Runtime guardrail…
Balancing Memory Pathways: Analyzing and Improving Memory Utilization in Hybrid LMs
Hyunji Lee, Joykirat Singh, Zaid Khan +5
Recurrent-attention hybrid language models (LMs), which interleave attention and recurrent layers, are increasingly used to combine the efficiency of the recurrent layers with the…
TeleTune: Evolving Agent Skills From Offline Telemetry
Justin Chih-Yao Chen, Elias Stengel-Eskin, Yan Chen +6
Computer-use agents need to capture procedural knowledge of how people use software. User telemetry offers a scalable source of this knowledge. However, learning reusable skills fr…
Evaluating Persistent Calibration under Evolving Model Knowledge
Victor Wang, Thomas Hofweber, Mohit Bansal +1
As AI systems move from static repositories to agents that are capable of continual adaptation and learning, maintaining their trustworthiness means equipping the models backing th…
CreativeInstruct: Scalably Teaching LLMs to Balance Quality, Creativity, and Diversity
Ananya Sahu, Mohit Bansal, Elias Stengel-Eskin
While post-training improves the capabilities of large language models (LLMs), it generally lowers their output diversity and creativity, negatively impacting tasks that explicitly…
Physics Question Scene Graph: Fine-grained Evaluation of Physical Plausibility in Text-to-Video Generation
Atin Pothiraj, Jaemin Cho, Yue Zhang +2
Video generation models are increasingly capable of producing realistic videos, but they still struggle to generate videos that follow basic physical laws. Compounding this is a la…
A History-Aware Visually Grounded Critic for Computer Use Agents
Jaewoo Lee, Zaid Khan, Archiki Prasad +7
Various test-time interventions for Computer Use Agents (CUAs), including critic models, have been developed to improve performance through pre-execution action evaluation in compl…
GPU Forecasters: Language Models as Selective Surrogates for Kernel Runtime Optimization
Zaid Khan, Justin Chih-Yao Chen, Jaemin Cho +2
GPU kernels are the workhorse of modern deep learning, and optimizing them (via evolutionary search or coding agents) usually requires repeated measurement on target hardware. Whil…
AVSD: Adaptive-View Self-Distillation by Balancing Consensus and Teacher-Specific Privileged Signals
Duy Nguyen, Hanqi Xiao, Archiki Prasad +7
Self-distillation enables language models to learn on-policy from their own trajectories by using the same model as both student and teacher, with the teacher being conditioned on…
MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems
Hyunji Lee, Justin Chih-Yao Chen, Joykirat Singh +3
Real-world agents operate over long and evolving horizons, where information is repeatedly updated and may interfere across memories, requiring accurate recall and aggregated reaso…
Cog-DRIFT: Exploration on Adaptively Reformulated Instances Enables Learning from Hard Reasoning Problems
Justin Chih-Yao Chen, Archiki Prasad, Zaid Khan +4
Reinforcement learning from verifiable rewards (RLVR) has improved the reasoning abilities of LLMs, yet a fundamental limitation remains: models cannot learn from problems that are…
Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind
Hanqi Xiao, Vaidehi Patil, Zaid Khan +3
As large language models (LLMs) become the engine behind conversational systems, their ability to reason about the intentions and states of their dialogue partners (i.e., form and…
Does AI See like Art Historians? Interpreting How Vision Language Models Recognize Artistic Style
Marvin Limpijankit, Milad Alshomary, Yassin Oulad Daoud +9
VLMs have become increasingly proficient at a range of computer vision tasks, such as visual question answering and object detection. This includes increasingly strong capabilities…
Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution
Nithin Sivakumaran, Shoubin Yu, Hyunji Lee +4
Chain-of-thought (CoT) reasoning sometimes fails to faithfully reflect the true computation of a large language model (LLM), hampering its utility in explaining how LLMs arrive at…
Conflict-Resolving and Sharpness-Aware Minimization for Generalized Knowledge Editing with Multiple Updates
Duy Nguyen, Hanqi Xiao, Archiki Prasad +3
Large language models (LLMs) rely on internal knowledge to solve many downstream tasks, making it crucial to keep them up to date. Since full retraining is expensive, prior work ha…
Routing with Generated Data: Annotation-Free LLM Skill Estimation and Expert Selection
Tianyi Niu, Justin Chih-Yao Chen, Genta Indra Winata +6
Large Language Model (LLM) routers dynamically select optimal models for given inputs. Existing approaches typically assume access to ground-truth labeled data, which is often unav…
DART: Leveraging Multi-Agent Disagreement for Tool Recruitment in Multimodal Reasoning
Nithin Sivakumaran, Justin Chih-Yao Chen, David Wan +4
Specialized visual tools can augment large language models or vision language models with expert knowledge (e.g., grounding, spatial reasoning, medical knowledge, etc.), but knowin…
PRInTS: Reward Modeling for Long-Horizon Information Seeking
Jaewoo Lee, Archiki Prasad, Justin Chih-Yao Chen +3
Information-seeking is a core capability for AI agents, requiring them to gather and reason over tool-generated information across long trajectories. However, such multi-step infor…
Gistify! Codebase-Level Understanding via Runtime Execution
Hyunji Lee, Minseon Kim, Chinmay Singh +10
As coding agents are increasingly deployed in large codebases, the need to automatically design challenging, codebase-level evaluation is central. We propose Gistify, a task where…
Think Right: Learning to Mitigate Under-Over Thinking via Adaptive, Attentive Compression
Joykirat Singh, Justin Chih-Yao Chen, Archiki Prasad +3
Recent thinking models are capable of solving complex reasoning tasks by scaling test-time compute, but this scaling should be allocated in line with task difficulty. On one hand,…
PoSh: Using Scene Graphs To Guide LLMs-as-a-Judge For Detailed Image Descriptions
Amith Ananthram, Elias Stengel-Eskin, Lorena A. Bradford +7
While vision-language models (VLMs) have advanced into detailed image description, evaluation remains a challenge. Standard metrics (e.g. CIDEr, SPICE) were designed for short text…
One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration
Zaid Khan, Archiki Prasad, Elias Stengel-Eskin +2
Symbolic world modeling requires inferring and representing an environment's transitional dynamics as an executable program. Prior work has focused on largely deterministic environ…