TrustAgent: Towards Safe and Trustworthy LLM-based Agents
Paper • 2402.01586 • Published
Rutgers-TRAIL
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
rrrrrrrrrrrrryan
authored 20
papers 10 days ago
Large Language Models As Faithful Explainers
Paper • 2402.04678 • Published
Mitigating Gender Bias in Captioning Systems
Paper • 2006.08315 • Published
LoRATK: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem
Paper • 2403.00108 • Published
CATP: Contextually Adaptive Token Pruning for Efficient and Enhanced Multimodal In-Context Learning
Paper • 2508.07871 • Published
CounterVQA: Evaluating and Improving Counterfactual Reasoning in Vision-Language Models for Video Understanding
Paper • 2511.19923 • Published
A Single Layer to Explain Them All:Understanding Massive Activations in Large Language Models
Paper • 2605.08504 • Published • 6
AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems
Paper • 2605.08715 • Published • 9
Micro-Defects Expose Macro-Fakes: Detecting AI-Generated Images via Local Distributional Shifts
Paper • 2605.09296 • Published • 4
Improving Visual Reasoning with Iterative Evidence Refinement
Paper • 2603.14117 • Published
MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory
Paper • 2605.15128 • Published • 66
TokenSeek: Memory Efficient Fine Tuning via Instance-Aware Token Ditching
Paper • 2601.19739 • Published
Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models
Paper • 2407.11282 • Published • 1
Assessing and Enhancing Large Language Models in Rare Disease Question-answering
Paper • 2408.08422 • Published
The Science of Detecting LLM-Generated Texts
Paper • 2303.07205 • Published
Disentangling Memory and Reasoning Ability in Large Language Models
Paper • 2411.13504 • Published • 1
Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics
Paper • 2411.13587 • Published
Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond
Paper • 2304.13712 • Published
Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model
Paper • 2305.15265 • Published • 1
Hallucinatory Image Tokens: A Training-free EAZY Approach on Detecting and Mitigating Object Hallucinations in LVLMs
Paper • 2503.07772 • Published • 1