University of Illinois at Urbana-Champaign

university

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

haopeng01 submitted a paper 5 days ago

RoPE Distinguishes Neither Positions Nor Tokens in Long Contexts, Provably

arkimjh submitted a paper 7 days ago

GRASP: Learning to Ground Social Reasoning in Multi-Person Non-Verbal Interactions

kaiyan289 submitted a paper 11 days ago

Boosting Reinforcement Learning with Verifiable Rewards via Randomly Selected Few-Shot Guidance

View all activity

Papers

Spreadsheet-RL: Advancing Large Language Model Agents on Realistic Spreadsheet Tasks via Reinforcement Learning

RoPE Distinguishes Neither Positions Nor Tokens in Long Contexts, Provably

View all Papers

submitted a paper to Daily Papers 5 days ago

RoPE Distinguishes Neither Positions Nor Tokens in Long Contexts, Provably

Paper • 2605.15514 • Published 11 days ago

submitted a paper to Daily Papers 7 days ago

GRASP: Learning to Ground Social Reasoning in Multi-Person Non-Verbal Interactions

Paper • 2605.15764 • Published 11 days ago • 3

submitted a paper to Daily Papers 11 days ago

Boosting Reinforcement Learning with Verifiable Rewards via Randomly Selected Few-Shot Guidance

Paper • 2605.15012 • Published 12 days ago • 4

submitted a paper to Daily Papers 11 days ago

RouteProfile: Elucidating the Design Space of LLM Profiles for Routing

Paper • 2605.00180 • Published 26 days ago • 30

submitted a paper to Daily Papers 12 days ago

Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation

Paper • 2605.12975 • Published 13 days ago • 9

submitted a paper to Daily Papers 13 days ago

The Many Faces of On-Policy Distillation: Pitfalls, Mechanisms, and Fixes

Paper • 2605.11182 • Published 15 days ago • 5

submitted a paper to Daily Papers 15 days ago

Who Prices Cognitive Labor in the Age of Agents? Compute-Anchored Wages

Paper • 2605.05558 • Published 18 days ago • 3

submitted a paper to Daily Papers 19 days ago

CreativityBench: Evaluating Agent Creative Reasoning via Affordance-Based Tool Repurposing

Paper • 2605.02910 • Published 20 days ago • 22

authored a paper 19 days ago

TRACE: Capability-Targeted Agentic Training

Paper • 2604.05336 • Published Apr 7 • 14

submitted a paper to Daily Papers 20 days ago

Agentic AI Systems Should Be Designed as Marginal Token Allocators

Paper • 2605.01214 • Published 24 days ago • 4

submitted a paper to Daily Papers about 1 month ago

LangFlow: Continuous Diffusion Rivals Discrete in Language Modeling

Paper • 2604.11748 • Published Apr 15 • 14

submitted a paper to Daily Papers about 1 month ago

Narrative-Driven Paper-to-Slide Generation via ArcDeck

Paper • 2604.11969 • Published Apr 13 • 7

submitted a paper to Daily Papers about 2 months ago

HandX: Scaling Bimanual Motion and Interaction Generation

Paper • 2603.28766 • Published Mar 30 • 12

submitted a paper to Daily Papers 2 months ago

Sparking Scientific Creativity via LLM-Driven Interdisciplinary Inspiration

Paper • 2603.12226 • Published Mar 12 • 4

submitted a paper to Daily Papers 3 months ago

Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data

Paper • 2602.21320 • Published Feb 24 • 12

submitted a paper to Daily Papers 3 months ago

Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs

Paper • 2602.07276 • Published Feb 7 • 11

submitted a paper to Daily Papers 3 months ago

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

Paper • 2602.07080 • Published Feb 6 • 6

submitted a paper to Daily Papers 4 months ago

Agentic Reasoning for Large Language Models

Paper • 2601.12538 • Published Jan 18 • 204

authored 2 papers 5 months ago

HandsOff: Labeled Dataset Generation With No Additional Human Annotations

Paper • 2212.12645 • Published Dec 24, 2022 • 1

Why do These Match? Explaining the Behavior of Image Similarity Models

Paper • 1905.10797 • Published May 26, 2019 • 1