Picture for Weipeng Chen

Weipeng Chen

VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs

Add code
Dec 02, 2024
Figure 1 for VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs
Figure 2 for VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs
Figure 3 for VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs
Figure 4 for VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs
Viaarxiv icon

KV Shifting Attention Enhances Language Modeling

Add code
Nov 29, 2024
Viaarxiv icon

Beyond Sight: Towards Cognitive Alignment in LVLM via Enriched Visual Knowledge

Add code
Nov 25, 2024
Viaarxiv icon

VersaTune: Harnessing Vertical Domain Insights for Multi-Ability LLM Supervised Fine-Tuning

Add code
Nov 24, 2024
Figure 1 for VersaTune: Harnessing Vertical Domain Insights for Multi-Ability LLM Supervised Fine-Tuning
Figure 2 for VersaTune: Harnessing Vertical Domain Insights for Multi-Ability LLM Supervised Fine-Tuning
Figure 3 for VersaTune: Harnessing Vertical Domain Insights for Multi-Ability LLM Supervised Fine-Tuning
Figure 4 for VersaTune: Harnessing Vertical Domain Insights for Multi-Ability LLM Supervised Fine-Tuning
Viaarxiv icon

VersaTune: Fine-Tuning Multi-Ability LLMs Efficiently

Add code
Nov 18, 2024
Figure 1 for VersaTune: Fine-Tuning Multi-Ability LLMs Efficiently
Figure 2 for VersaTune: Fine-Tuning Multi-Ability LLMs Efficiently
Figure 3 for VersaTune: Fine-Tuning Multi-Ability LLMs Efficiently
Figure 4 for VersaTune: Fine-Tuning Multi-Ability LLMs Efficiently
Viaarxiv icon

From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning

Add code
Nov 06, 2024
Figure 1 for From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning
Figure 2 for From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning
Figure 3 for From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning
Figure 4 for From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning
Viaarxiv icon

HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems

Add code
Nov 05, 2024
Viaarxiv icon

Beyond Filtering: Adaptive Image-Text Quality Enhancement for MLLM Pretraining

Add code
Oct 21, 2024
Viaarxiv icon

Baichuan Alignment Technical Report

Add code
Oct 19, 2024
Figure 1 for Baichuan Alignment Technical Report
Figure 2 for Baichuan Alignment Technical Report
Figure 3 for Baichuan Alignment Technical Report
Figure 4 for Baichuan Alignment Technical Report
Viaarxiv icon

Exploring the Design Space of Visual Context Representation in Video MLLMs

Add code
Oct 17, 2024
Figure 1 for Exploring the Design Space of Visual Context Representation in Video MLLMs
Figure 2 for Exploring the Design Space of Visual Context Representation in Video MLLMs
Figure 3 for Exploring the Design Space of Visual Context Representation in Video MLLMs
Figure 4 for Exploring the Design Space of Visual Context Representation in Video MLLMs
Viaarxiv icon