Picture for Rui Pan

Rui Pan

Subjective Perspectives within Learned Representations Predict High-Impact Innovation

Add code
Jun 05, 2025
Viaarxiv icon

MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning

Add code
May 30, 2025
Viaarxiv icon

AstroMLab 4: Benchmark-Topping Performance in Astronomy Q&A with a 70B-Parameter Domain-Specialized Reasoning Model

Add code
May 23, 2025
Viaarxiv icon

SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning

Add code
Apr 10, 2025
Viaarxiv icon

ASGO: Adaptive Structured Gradient Optimization

Add code
Mar 26, 2025
Viaarxiv icon

MA-LoT: Multi-Agent Lean-based Long Chain-of-Thought Reasoning enhances Formal Theorem Proving

Add code
Mar 05, 2025
Viaarxiv icon

Adapt-Pruner: Adaptive Structural Pruning for Efficient Small Language Model Training

Add code
Feb 05, 2025
Viaarxiv icon

Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback

Add code
Dec 20, 2024
Figure 1 for Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback
Figure 2 for Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback
Figure 3 for Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback
Figure 4 for Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback
Viaarxiv icon

Entropy-Regularized Process Reward Model

Add code
Dec 15, 2024
Viaarxiv icon

RAGServe: Fast Quality-Aware RAG Systems with Configuration Adaptation

Add code
Dec 13, 2024
Viaarxiv icon