PPTDSL

PPTDSL's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Articles

XINLI1997 

authored 2 papers 14 days ago

Share the Symbol, Not the Vector: Training-Free Fact Communication Across Language Models

Paper • 2610.19696 • Published 15 days ago • 21

Many Right Answers, One Training Example: Removing Responder Noise from GRPO for LLM Recommenders

Paper • 2610.17771 • Published 16 days ago • 80

XINLI1997 

submitted 2 papers to Daily Papers 14 days ago

Many Right Answers, One Training Example: Removing Responder Noise from GRPO for LLM Recommenders

Paper • 2610.17771 • Published 16 days ago • 80

Share the Symbol, Not the Vector: Training-Free Fact Communication Across Language Models

Paper • 2610.19696 • Published 15 days ago • 21

XINLI1997 

authored a paper 15 days ago

AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards

Paper • 2610.18860 • Published 16 days ago • 138

XINLI1997 

authored 2 papers about 1 month ago

Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation

Paper • 2609.35347 • Published Sep 28 • 183

Measuring Collapse and Correction in Homogeneous-Panel LLM Debate

Paper • 2609.35279 • Published Sep 28 • 5

XINLI1997 

submitted 2 papers to Daily Papers about 1 month ago

Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation

Paper • 2609.35347 • Published Sep 28 • 183

Measuring Collapse and Correction in Homogeneous-Panel LLM Debate

Paper • 2609.35279 • Published Sep 28 • 5

XINLI1997 

authored a paper 6 months ago

The Extrapolation Cliff in On-Policy Distillation of Near-Deterministic Structured Outputs

Paper • 2605.08737 • Published May 9 • 3

XINLI1997 

submitted a paper to Daily Papers 6 months ago

The Extrapolation Cliff in On-Policy Distillation of Near-Deterministic Structured Outputs

Paper • 2605.08737 • Published May 9 • 3

XINLI1997 

authored 6 papers about 1 year ago

Beyond Correctness: Evaluating Subjective Writing Preferences Across Cultures

Paper • 2510.14616 • Published Oct 16, 2025 • 13

COIG-Writer: A High-Quality Dataset for Chinese Creative Writing with Thought Processes

Paper • 2510.14763 • Published Oct 16, 2025 • 14

Re:Form -- Reducing Human Priors in Scalable Formal Software Verification with RL in LLMs: A Preliminary Study on Dafny

Paper • 2507.16331 • Published Jul 22, 2025 • 22

WirelessMathLM: Teaching Mathematical Reasoning for LLMs in Wireless Communications with Reinforcement Learning

Paper • 2509.23219 • Published Sep 27, 2025 • 19

Local Success Does Not Compose: Benchmarking Large Language Models for Compositional Formal Verification

Paper • 2509.23061 • Published Sep 27, 2025 • 7

WirelessMathBench: A Mathematical Modeling Benchmark for LLMs in Wireless Communications

Paper • 2505.14354 • Published May 20, 2025 • 2