ICIP

university

https://www.icip.org.cn

AI & ML interests

None defined yet.

Recent Activity

tianyumyum authored a paper 1 day ago

SCI-AGENT-EXAM: Benchmarking Agents on Scientific Research Tasks

tianyumyum authored a paper 1 day ago

Before the Action: Benchmarking LLMs on Prospective Hypothesis Discovery

Bowieee submitted a paper 3 months ago

From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents

View all activity

Papers

From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents

Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination

View all Papers

authored 2 papers 1 day ago

SCI-AGENT-EXAM: Benchmarking Agents on Scientific Research Tasks

Paper • 2610.32441 • Published 13 days ago • 1

Before the Action: Benchmarking LLMs on Prospective Hypothesis Discovery

Paper • 2607.15766 • Published Jul 17

submitted a paper to Daily Papers 3 months ago

From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents

Paper • 2608.16002 • Published Aug 19 • 7

submitted a paper to Daily Papers 4 months ago

ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation

Paper • 2607.13124 • Published Jul 14 • 15

submitted a paper to Daily Papers 4 months ago

ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models

Paper • 2606.23404 • Published Jun 22 • 5

submitted a paper to Daily Papers 5 months ago

Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination

Paper • 2605.31058 • Published May 29 • 3

updated a dataset 5 months ago

ICIP/ADR

Viewer • Updated May 29 • 5k • 15 • 2

published a dataset 5 months ago

ICIP/ADR

Viewer • Updated May 29 • 5k • 15 • 2

submitted a paper to Daily Papers 6 months ago

Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards

Paper • 2605.14539 • Published May 14 • 6

submitted 2 papers to Daily Papers 7 months ago

Beyond Text-Dominance: Understanding Modality Preference of Omni-modal Large Language Models

Paper • 2604.16902 • Published Apr 18 • 5

Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces

Paper • 2604.08362 • Published Apr 9 • 12

submitted a paper to Daily Papers 8 months ago

Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards

Paper • 2603.09117 • Published Mar 10 • 10

updated a collection 8 months ago

PPTAgent

https://arxiv.org/abs/2501.03936 • 5 items • Updated Mar 9 • 1

authored a paper 8 months ago

DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation

Paper • 2602.22839 • Published Feb 26 • 4

updated a collection 8 months ago

DeepPresenter

http://arxiv.org/abs/2602.22839 • 5 items • Updated Mar 9 • 3

submitted a paper to Daily Papers 8 months ago

DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation

Paper • 2602.22839 • Published Feb 26 • 4

updated a collection 8 months ago

DeepPresenter

http://arxiv.org/abs/2602.22839 • 5 items • Updated Mar 9 • 3