Duke University

university

Verified

https://duke.edu

AI & ML interests

None defined yet.

authored 2 papers 2 months ago

MPCEval: A Benchmark for Multi-Party Conversation Generation

Paper • 2603.04969 • Published Mar 5

TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents

Paper • 2606.28480 • Published Jun 26 • 48

authored a paper 2 months ago

Rethinking Pulmonary Embolism Segmentation: A Study of Current Approaches and Challenges with an Open Weight Model

Paper • 2509.18308 • Published Apr 29

authored a paper 2 months ago

Controlled Low-Rank Adaptation with Subspace Regularization for Continued Training on Large Language Models

Paper • 2410.16801 • Published Mar 21, 2025

authored a paper 5 months ago

Batch-of-Thought: Cross-Instance Learning for Enhanced LLM Reasoning

Paper • 2601.02950 • Published Mar 7 • 1

authored a paper 6 months ago

T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasoning

Paper • 2603.03790 • Published Mar 4 • 122

authored 2 papers 6 months ago

MUSE: A Run-Centric Platform for Multimodal Unified Safety Evaluation of Large Language Models

Paper • 2603.02482 • Published Mar 3 • 3

T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasoning

Paper • 2603.03790 • Published Mar 4 • 122

submitted a paper to Daily Papers 6 months ago

MUSE: A Run-Centric Platform for Multimodal Unified Safety Evaluation of Large Language Models

Paper • 2603.02482 • Published Mar 3 • 3

authored a paper 7 months ago

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

Paper • 2602.12670 • Published Feb 13 • 65

updated a Space 7 months ago

README

published a Space 9 months ago

README

authored 3 papers 11 months ago

AsyncVoice Agent: Real-Time Explanation for LLM Planning and Reasoning

Paper • 2510.16156 • Published Oct 17, 2025 • 2

Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play

Paper • 2509.25541 • Published Sep 29, 2025 • 142

Voice Evaluation of Reasoning Ability: Diagnosing the Modality-Induced Performance Gap

Paper • 2509.26542 • Published Sep 30, 2025 • 10

authored a paper about 1 year ago

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models

Paper • 2505.19235 • Published May 25, 2025 • 4

authored 4 papers over 1 year ago

Angles Don't Lie: Unlocking Training-Efficient RL Through the Model's Own Signals

Paper • 2506.02281 • Published Jun 2, 2025 • 4

HippoMM: Hippocampal-inspired Multimodal Memory for Long Audiovisual Event Understanding

Paper • 2504.10739 • Published Apr 14, 2025 • 2

Muskits-ESPnet: A Comprehensive Toolkit for Singing Voice Synthesis in New Paradigm

Paper • 2409.07226 • Published Sep 11, 2024 • 1

Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey

Paper • 2407.21794 • Published Jul 31, 2024 • 6