University of Illinois at Urbana-Champaign

university

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

gasolsun submitted a paper 6 days ago

Ask to Distill: Learning to Synthesize Data for On-Policy Distillation

jizej submitted a paper 8 days ago

Competence-Based Evaluation of Logical Reasoning in Large Language Models

JackBAI submitted a paper 14 days ago

Enabling Token-wise Importance Sampling in Off-Policy RLVR with Proximal KL Regularization

View all activity

Papers

Memory Tax: Dissecting the Net Value of Agent Memory

Ask to Distill: Learning to Synthesize Data for On-Policy Distillation

View all Papers

UIUC-CS 's papers 70

Submitted by

Xuan He

Memory Tax: Dissecting the Net Value of Agent Memory

UIUC-CS

University of Illinois at Urbana-Champaign

Submitted by

Jiashuo Sun

Ask to Distill: Learning to Synthesize Data for On-Policy Distillation

UIUC-CS

University of Illinois at Urbana-Champaign

Submitted by

Jize Jiang

Competence-Based Evaluation of Logical Reasoning in Large Language Models

UIUC-CS

University of Illinois at Urbana-Champaign

Submitted by

HAO BAI

Enabling Token-wise Importance Sampling in Off-Policy RLVR with Proximal KL Regularization

UIUC-CS

University of Illinois at Urbana-Champaign

Submitted by

QIUSI ZHAN

Understanding and Enhancing Backdoor Persistency in LLM Agent Post-Training

UIUC-CS

University of Illinois at Urbana-Champaign

Submitted by

Fangxu

CURIO: Curiosity-Driven Test-Time Learning for Open-Ended Discovery

UIUC-CS

University of Illinois at Urbana-Champaign

Submitted by

Jiateng Liu

LMBuild: Evaluating LLM Agents for Generating Buildable and Functional Structures

UIUC-CS

University of Illinois at Urbana-Champaign

Submitted by

siqi zhu

From Gradients to Capabilities: Understanding Multi-Teacher On-Policy Distillation

UIUC-CS

University of Illinois at Urbana-Champaign

2

Submitted by

Hui Ren

Hierarchical Continuous Diffusion Language Models

UIUC-CS

University of Illinois at Urbana-Champaign

Submitted by

Sirui Xu

InterEvolve: Test-Time Evolution of Reward Programs for Humanoid Loco-Manipulation

UIUC-CS

University of Illinois at Urbana-Champaign

Submitted by

Shubhang Bhatnagar

ReGain: Restoring Subject Fidelity in Personalization on Synthetic Images

UIUC-CS

University of Illinois at Urbana-Champaign

Submitted by

bingxuan li

MotorMind: Scaffolding General Vision Language Models for Zero-Shot Robot Manipulation

UIUC-CS

University of Illinois at Urbana-Champaign