University of Illinois at Urbana-Champaign

university

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

p-song1 submitted a paper 3 days ago

Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs

bruno888 submitted a paper 4 days ago

CodeCircuit: Toward Inferring LLM-Generated Code Correctness via Attribution Graphs

jiaruz2 submitted a paper 23 days ago

Agentic Reasoning for Large Language Models

View all activity

Papers

Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs

CodeCircuit: Toward Inferring LLM-Generated Code Correctness via Attribution Graphs

View all Papers

UIUC-CS 's Papers 20

Submitted by

Peiyang Song

Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs

UIUC-CS

University of Illinois at Urbana-Champaign

2

Submitted by

Yicheng He

CodeCircuit: Toward Inferring LLM-Generated Code Correctness via Attribution Graphs

UIUC-CS

University of Illinois at Urbana-Champaign

Submitted by

Dylan

Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning

UIUC-CS

University of Illinois at Urbana-Champaign

3

Submitted by

Jiaru Zou

Agentic Reasoning for Large Language Models

UIUC-CS

University of Illinois at Urbana-Champaign

Submitted by

taesiri

When Reasoning Meets Its Laws

UIUC-CS

University of Illinois at Urbana-Champaign

Submitted by

Tarun Suresh

BEAVER: An Efficient Deterministic LLM Verifier

UIUC-CS

University of Illinois at Urbana-Champaign

Submitted by

Shaowei Liu

Visual Sync: Multi-Camera Synchronization via Cross-View Object Motion

UIUC-CS

University of Illinois at Urbana-Champaign

Submitted by

taesiri

VisPlay: Self-Evolving Vision-Language Models from Images

UIUC-CS

University of Illinois at Urbana-Champaign

Submitted by

siqi zhu

Multi-Agent Evolve: LLM Self-Improve through Co-evolution

UIUC-CS

University of Illinois at Urbana-Champaign

Submitted by

Rui Yang

ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learning

UIUC-CS

University of Illinois at Urbana-Champaign

Submitted by

siqi zhu

GTAlign: Game-Theoretic Alignment of LLM Assistants for Mutual Welfare

UIUC-CS

University of Illinois at Urbana-Champaign

Submitted by

Jesse Mel

How to Teach Large Multimodal Models New Skills

UIUC-CS

University of Illinois at Urbana-Champaign

Submitted by

Jipeng Lyu

SCas4D: Structural Cascaded Optimization for Boosting Persistent 4D Novel View Synthesis

UIUC-CS

University of Illinois at Urbana-Champaign

Submitted by

Jiashuo Sun

GRACE: Generative Representation Learning via Contrastive Policy Optimization

UIUC-CS

University of Illinois at Urbana-Champaign

Submitted by

KunlunZhu

Where LLM Agents Fail and How They can Learn From Failures

UIUC-CS

University of Illinois at Urbana-Champaign

Misaligning Reasoning with Answers -- A Framework for Assessing LLM CoT Robustness

UIUC-CS

University of Illinois at Urbana-Champaign

Towards Hierarchical Rectified Flow

UIUC-CS

University of Illinois at Urbana-Champaign

Towards Universal Certified Robustness with Multi-Norm Training

UIUC-CS

University of Illinois at Urbana-Champaign

RAMP: Boosting Adversarial Robustness Against Multiple l_p Perturbations for Universal Robustness

UIUC-CS

University of Illinois at Urbana-Champaign

Evaluating Uncertainty Quantification approaches for Neural PDEs in scientific applications

UIUC-CS

University of Illinois at Urbana-Champaign