Nguyen Van Thanh

NguyenVanThanhHust's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

upvoted 20 papers 1 day ago

When to Speak, When to Abstain: Contrastive Decoding with Abstention

Paper • 2412.12527 • Published 4 days ago • 4

SUGAR: Subject-Driven Video Customization in a Zero-Shot Manner

Paper • 2412.10533 • Published 8 days ago • 5

MIVE: New Design and Benchmark for Multi-Instance Video Editing

Paper • 2412.12877 • Published 4 days ago • 4

VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation

Paper • 2412.10704 • Published 7 days ago • 10

Proposer-Agent-Evaluator(PAE): Autonomous Skill Discovery For Foundation Model Internet Agents

Paper • 2412.13194 • Published 4 days ago • 10

Feather the Throttle: Revisiting Visual Token Pruning for Vision-Language Model Acceleration

Paper • 2412.13180 • Published 4 days ago • 11

Emergence of Abstractions: Concept Encoding and Decoding Mechanism for In-Context Learning in Transformers

Paper • 2412.12276 • Published 5 days ago • 13

Compressed Chain of Thought: Efficient Reasoning Through Dense Representations

Paper • 2412.13171 • Published 4 days ago • 29

Multi-Dimensional Insights: Benchmarking Real-World Personalization in Large Multimodal Models

Paper • 2412.12606 • Published 4 days ago • 40

OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain

Paper • 2412.13018 • Published 4 days ago • 39

Are Your LLMs Capable of Stable Reasoning?

Paper • 2412.13147 • Published 4 days ago • 79

Star Attention: Efficient LLM Inference over Long Sequences

Paper • 2411.17116 • Published 25 days ago • 47

TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks

Paper • 2412.14161 • Published 3 days ago • 40

AniDoc: Animation Creation Made Easier

Paper • 2412.14173 • Published 3 days ago • 39

Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference

Paper • 2412.13663 • Published 3 days ago • 86

Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN

Paper • 2412.13795 • Published 3 days ago • 18

FashionComposer: Compositional Fashion Image Generation

Paper • 2412.14168 • Published 3 days ago • 15

No More Adam: Learning Rate Scaling at Initialization is All You Need

Paper • 2412.11768 • Published 5 days ago • 36

Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning

Paper • 2412.12953 • Published 4 days ago • 11

GUI Agents: A Survey

Paper • 2412.13501 • Published 3 days ago • 16