Carnegie Mellon University

university

Verified

https://www.cmu.edu

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

fjzzq2002 submitted a paper 5 days ago

Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops

xiangchensong authored a paper 6 days ago

CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?

xiangchensong authored a paper 6 days ago

CausaLab: A Scalable Environment for Interactive Causal Discovery Toward AI Scientists

View all activity

Papers

Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops

K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts

View all Papers

submitted a paper to Daily Papers 5 days ago

Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops

Paper • 2606.08960 • Published 6 days ago • 1

submitted 2 papers to Daily Papers 12 days ago

Same Question, Different Source, Different Answer: Auditing Source-Dependence in Medical Multi-Source RAG

Paper • 2605.29084 • Published 18 days ago • 1

The Chain Holds, the Answer Folds: Trace-Answer Dissociation in Reasoning Models Under Adversarial Pressure

Paper • 2605.29087 • Published 18 days ago • 1

submitted a paper to Daily Papers 12 days ago

K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts

Paper • 2606.02404 • Published 13 days ago • 56

submitted 2 papers to Daily Papers 15 days ago

CONF-KV: Confidence-Aware KV Cache Eviction with Mixed-Precision Storage for Long-Horizon LLM

Paper • 2605.24786 • Published 21 days ago • 9

PANDO: Efficient Multimodal AI Agents via Online Skill Distillation

Paper • 2605.24785 • Published 19 days ago • 11

submitted a paper to Daily Papers 16 days ago

Multi-view Consistent 3D Gaussian Head Avatars 'without' Multi-view Generation

Paper • 2605.25220 • Published 21 days ago • 7

submitted a paper to Daily Papers 20 days ago

LatentUMM: Dual Latent Alignment for Unified Multimodal Models

Paper • 2605.17766 • Published 27 days ago • 8

submitted a paper to Daily Papers 24 days ago

On the limits and opportunities of AI reviewers: Reviewing the reviews of Nature-family papers with 45 expert scientists

Paper • 2605.20668 • Published 25 days ago • 12

submitted a paper to Daily Papers 24 days ago

Base Models Look Human To AI Detectors

Paper • 2605.19516 • Published 26 days ago • 2

authored 5 papers 24 days ago

Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks

Paper • 2204.07705 • Published Apr 16, 2022 • 2

Representation Learning for Conversational Data using Discourse Mutual Information Maximization

Paper • 2112.05787 • Published Dec 4, 2021

PBEBench: A Multi-Step Programming by Examples Reasoning Benchmark inspired by Historical Linguistics

Paper • 2505.23126 • Published May 29, 2025

PragWorld: A Benchmark Evaluating LLMs' Local World Model under Minimal Linguistic Alterations and Conversational Dynamics

Paper • 2511.13021 • Published Nov 17, 2025

ReaComp: Compiling LLM Reasoning into Symbolic Solvers for Efficient Program Synthesis

Paper • 2605.05485 • Published May 6

submitted a paper to Daily Papers 26 days ago

MixSD: Mixed Contextual Self-Distillation for Knowledge Injection

Paper • 2605.16865 • Published 29 days ago • 8

submitted a paper to Daily Papers about 1 month ago

From Generalist to Specialist Representation

Paper • 2605.12733 • Published May 12 • 2

submitted a paper to Daily Papers about 1 month ago

Auto Research with Specialist Agents Develops Effective and Non-Trivial Training Recipes

Paper • 2605.05724 • Published May 7 • 15

submitted a paper to Daily Papers about 2 months ago

EmbodiedMidtrain: Bridging the Gap between Vision-Language Models and Vision-Language-Action Models via Mid-training

Paper • 2604.20012 • Published Apr 21 • 5

submitted a paper to Daily Papers about 2 months ago

Building a Precise Video Language with Human-AI Oversight

Paper • 2604.21718 • Published Apr 22 • 17