Feather the Throttle: Revisiting Visual Token Pruning for Vision-Language Model Acceleration
Paper
•
2412.13180
•
Published
•
12
Pratyay Banerjee
Neilblaze
AI & ML interests
HCI, Computer Vision, Object Detection, Pattern Recognition, NLP, Supervised Learning
Recent Activity
upvoted
a
paper
2 days ago
Compressed Chain of Thought: Efficient Reasoning Through Dense
Representations
Organizations
Neilblaze's activity
upvoted
15
papers
2 days ago
Compressed Chain of Thought: Efficient Reasoning Through Dense Representations
Paper
•
2412.13171
•
Published
•
30
Multi-Dimensional Insights: Benchmarking Real-World Personalization in Large Multimodal Models
Paper
•
2412.12606
•
Published
•
40
OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain
Paper
•
2412.13018
•
Published
•
39
Are Your LLMs Capable of Stable Reasoning?
Paper
•
2412.13147
•
Published
•
82
AntiLeak-Bench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge
Paper
•
2412.13670
•
Published
•
4
VidTok: A Versatile and Open-Source Video Tokenizer
Paper
•
2412.13061
•
Published
•
6
RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment
Paper
•
2412.13746
•
Published
•
8
ChatDiT: A Training-Free Baseline for Task-Agnostic Free-Form Chatting with Diffusion Transformers
Paper
•
2412.12571
•
Published
•
7
Autoregressive Video Generation without Vector Quantization
Paper
•
2412.14169
•
Published
•
12
FastVLM: Efficient Vision Encoding for Vision Language Models
Paper
•
2412.13303
•
Published
•
12
No More Adam: Learning Rate Scaling at Initialization is All You Need
Paper
•
2412.11768
•
Published
•
37
AniDoc: Animation Creation Made Easier
Paper
•
2412.14173
•
Published
•
44
TOMG-Bench: Evaluating LLMs on Text-based Open Molecule Generation
Paper
•
2412.14642
•
Published
•
4
Hermes 3 Technical Report
Paper
•
2408.11857
•
Published
•
41
upvoted
5
papers
6 days ago
SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints
Paper
•
2412.07760
•
Published
•
49
ChatGen: Automatic Text-to-Image Generation From FreeStyle Chatting
Paper
•
2411.17176
•
Published
•
22
TryOffDiff: Virtual-Try-Off via High-Fidelity Garment Reconstruction using Diffusion Models
Paper
•
2411.18350
•
Published
•
22
Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning
Paper
•
2411.18203
•
Published
•
30
Reverse Thinking Makes LLMs Stronger Reasoners
Paper
•
2411.19865
•
Published
•
19