Gies College of Business at UIUC

university

AI & ML interests

None defined yet.

authored a paper about 1 month ago

ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning

Paper • 2603.10160 • Published Mar 10 • 26

authored a paper 2 months ago

Toward Cognitive Supersensing in Multimodal Large Language Model

Paper • 2602.01541 • Published Feb 2 • 16

authored a paper 3 months ago

Agentic Reasoning for Large Language Models

Paper • 2601.12538 • Published Jan 18 • 202

authored 3 papers 5 months ago

Drive as You Speak: Enabling Human-Like Interaction with Large Language Models in Autonomous Vehicles

Paper • 2309.10228 • Published Sep 19, 2023

On-Board Vision-Language Models for Personalized Autonomous Vehicle Motion Control: System Design and Real-World Validation

Paper • 2411.11913 • Published Nov 17, 2024

MedSAM3: Delving into Segment Anything with Medical Concepts

Paper • 2511.19046 • Published Nov 24, 2025 • 55

authored 4 papers 7 months ago

NTK-approximating MLP Fusion for Efficient Language Model Fine-tuning

Paper • 2307.08941 • Published Jul 18, 2023 • 1

Towards Unified Multi-Modal Personalization: Large Vision-Language Models for Generative Recommendation and Beyond

Paper • 2403.10667 • Published Mar 15, 2024 • 1

SelfElicit: Your Language Model Secretly Knows Where is the Relevant Evidence

Paper • 2502.08767 • Published Feb 12, 2025

WAPITI: A Watermark for Finetuned Open-Source LLMs

Paper • 2410.06467 • Published Oct 9, 2024

authored 2 papers 10 months ago

SocialGesture: Delving into Multi-person Gesture Understanding

Paper • 2504.02244 • Published Apr 3, 2025

Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs

Paper • 2506.21656 • Published Jun 26, 2025 • 16

authored a paper 10 months ago

Saffron-1: Towards an Inference Scaling Paradigm for LLM Safety Assurance

Paper • 2506.06444 • Published Jun 6, 2025 • 73

authored a paper 12 months ago

CORG: Generating Answers from Complex, Interrelated Contexts

Paper • 2505.00023 • Published Apr 25, 2025 • 9

authored a paper about 1 year ago

BlobCtrl: A Unified and Flexible Framework for Element-level Image Generation and Editing

Paper • 2503.13434 • Published Mar 17, 2025 • 27

authored a paper about 1 year ago

SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution

Paper • 2502.18449 • Published Feb 25, 2025 • 75

authored a paper over 1 year ago

DisPose: Disentangling Pose Guidance for Controllable Human Image Animation

Paper • 2412.09349 • Published Dec 12, 2024 • 8

authored a paper over 1 year ago

SciCode: A Research Coding Benchmark Curated by Scientists

Paper • 2407.13168 • Published Jul 18, 2024 • 17

authored 2 papers almost 2 years ago

If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents

Paper • 2401.00812 • Published Jan 1, 2024 • 12

What is the Visual Cognition Gap between Humans and Multimodal LLMs?

Paper • 2406.10424 • Published Jun 14, 2024