Picture for Zefan Cai

Zefan Cai

AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence

Add code
Feb 19, 2025
Viaarxiv icon

HeadInfer: Memory-Efficient LLM Inference by Head-wise Offloading

Add code
Feb 18, 2025
Viaarxiv icon

Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey

Add code
Dec 30, 2024
Viaarxiv icon

No Preference Left Behind: Group Distributional Preference Optimization

Add code
Dec 28, 2024
Figure 1 for No Preference Left Behind: Group Distributional Preference Optimization
Figure 2 for No Preference Left Behind: Group Distributional Preference Optimization
Figure 3 for No Preference Left Behind: Group Distributional Preference Optimization
Figure 4 for No Preference Left Behind: Group Distributional Preference Optimization
Viaarxiv icon

Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning

Add code
Oct 28, 2024
Figure 1 for Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning
Figure 2 for Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning
Figure 3 for Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning
Figure 4 for Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning
Viaarxiv icon

COMMA: A Communicative Multimodal Multi-Agent Benchmark

Add code
Oct 10, 2024
Figure 1 for COMMA: A Communicative Multimodal Multi-Agent Benchmark
Figure 2 for COMMA: A Communicative Multimodal Multi-Agent Benchmark
Figure 3 for COMMA: A Communicative Multimodal Multi-Agent Benchmark
Figure 4 for COMMA: A Communicative Multimodal Multi-Agent Benchmark
Viaarxiv icon

Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models

Add code
Oct 10, 2024
Figure 1 for Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models
Figure 2 for Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models
Figure 3 for Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models
Figure 4 for Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models
Viaarxiv icon

A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation

Add code
Oct 02, 2024
Figure 1 for A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation
Figure 2 for A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation
Figure 3 for A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation
Figure 4 for A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation
Viaarxiv icon

Towards a Unified View of Preference Learning for Large Language Models: A Survey

Add code
Sep 04, 2024
Figure 1 for Towards a Unified View of Preference Learning for Large Language Models: A Survey
Figure 2 for Towards a Unified View of Preference Learning for Large Language Models: A Survey
Figure 3 for Towards a Unified View of Preference Learning for Large Language Models: A Survey
Figure 4 for Towards a Unified View of Preference Learning for Large Language Models: A Survey
Viaarxiv icon

LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback

Add code
Jun 30, 2024
Figure 1 for LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback
Figure 2 for LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback
Figure 3 for LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback
Figure 4 for LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback
Viaarxiv icon