Mayank Bhaskar's picture

Mayank Bhaskar

cataluna84

·

AI & ML interests

Research interest includes anything that moves or in processing things that are on the audible spectrum and has recently been seduced by RL Theory, GNNs, Transformers & applications of them in solving self-driving autonomous systems including vehicles, drones, and robots.

Articles

Fine tuning CLIP with Remote Sensing (Satellite) images and captions

Organizations

cataluna84's activity

upvoted a paper about 5 hours ago

Law of the Weakest Link: Cross Capabilities of Large Language Models

Paper • 2409.19951 • Published 5 days ago • 46

upvoted 4 papers 2 days ago

UniAff: A Unified Representation of Affordances for Tool Usage and Articulation with Vision-Language Models

Paper • 2409.20551 • Published 4 days ago • 13

Enable Language Models to Implicitly Learn Self-Improvement From Data

Paper • 2310.00898 • Published Oct 2, 2023 • 23

Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement

Paper • 2409.12122 • Published 16 days ago • 1

MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning

Paper • 2409.20566 • Published 4 days ago • 41

upvoted 2 papers 3 days ago

MIO: A Foundation Model on Multimodal Tokens

Paper • 2409.17692 • Published 9 days ago • 45

Emu3: Next-Token Prediction is All You Need

Paper • 2409.18869 • Published 7 days ago • 71

upvoted a collection 4 days ago

Emu3

3 items • Updated 8 days ago • 47

upvoted an article 8 days ago

Article

Llama can now see and run on your device - welcome Llama 3.2

10 days ago

• 136

upvoted 8 papers 10 days ago

Reflecting Reality: Enabling Diffusion Models to Produce Faithful Mirror Reflections

Paper • 2409.14677 • Published 12 days ago • 14

MuCodec: Ultra Low-Bitrate Music Codec

Paper • 2409.13216 • Published 15 days ago • 22

Colorful Diffuse Intrinsic Image Decomposition in the Wild

Paper • 2409.13690 • Published 14 days ago • 12

V^3: Viewing Volumetric Videos on Mobiles via Streamable 2D Dynamic Gaussians

Paper • 2409.13648 • Published 14 days ago • 9

YesBut: A High-Quality Annotated Multimodal Dataset for evaluating Satire Comprehension capability of Vision-Language Models

Paper • 2409.13592 • Published 14 days ago • 45

Imagine yourself: Tuning-Free Personalized Image Generation

Paper • 2409.13346 • Published 15 days ago • 65

SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?

Paper • 2402.01832 • Published Feb 2 • 6

KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

Paper • 2401.18079 • Published Jan 31 • 7

upvoted a collection 10 days ago

KV Cache Compression

2 items • Updated 10 days ago • 1

upvoted a paper 11 days ago

MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting

Paper • 2409.14393 • Published 12 days ago • 7

upvoted 7 papers 12 days ago

Sapiens: Foundation for Human Vision Models

Paper • 2408.12569 • Published Aug 22 • 86

OLMo: Accelerating the Science of Language Models

Paper • 2402.00838 • Published Feb 1 • 79

FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

Paper • 2307.08691 • Published Jul 17, 2023 • 8

FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness

Paper • 2205.14135 • Published May 27, 2022 • 10

FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision

Paper • 2407.08608 • Published Jul 11 • 1

ColPali: Efficient Document Retrieval with Vision Language Models

Paper • 2407.01449 • Published Jun 27 • 41

3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion

Paper • 2409.12957 • Published 15 days ago • 17

upvoted 2 papers 13 days ago

InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoning

Paper • 2409.12568 • Published 16 days ago • 46

OmniGen: Unified Image Generation

Paper • 2409.11340 • Published 17 days ago • 80

upvoted 2 papers 14 days ago

Training Language Models to Self-Correct via Reinforcement Learning

Paper • 2409.12917 • Published 15 days ago • 127

GRIN: GRadient-INformed MoE

Paper • 2409.12136 • Published 16 days ago • 14

upvoted a collection 15 days ago

Moshi v0.1 Release

MLX, Candle & PyTorch model checkpoints released as part of the Moshi release from Kyutai. Run inference via: https://github.com/kyutai-labs/moshi • 13 items • Updated 16 days ago • 201

upvoted 2 papers 15 days ago

Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Paper • 2409.12191 • Published 16 days ago • 69

Qwen2.5-Coder Technical Report

Paper • 2409.12186 • Published 16 days ago • 120

upvoted 3 collections 15 days ago

Qwen2.5-Math

Math-specific model series based on Qwen2.5 • 9 items • Updated 12 days ago • 34

Qwen2.5-Coder

Code-specific model series based on Qwen2.5 • 14 items • Updated 9 days ago • 69

Qwen2.5

Qwen2.5 language models, including pretrained and instruction-tuned models of 7 sizes, including 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B. • 45 items • Updated 16 days ago • 220

upvoted an article 16 days ago

Article

Fine-tuning LLMs to 1.58bit: extreme quantization made easy

17 days ago

• 144

upvoted a paper 18 days ago

Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo

Paper • 2404.17546 • Published Apr 26 • 1

upvoted an article 21 days ago

Article

Accelerate 1.0.0

22 days ago

• 34

upvoted 2 papers 23 days ago

Text-to-Image Generation Via Energy-Based CLIP

Paper • 2408.17046 • Published Aug 30 • 2

The AdEMAMix Optimizer: Better, Faster, Older

Paper • 2409.03137 • Published 30 days ago • 5

upvoted an article 28 days ago

Article

ColPali: Efficient Document Retrieval with Vision Language Models 👀

By

•

Jul 5

• 109

upvoted a collection 29 days ago

LLaVA-Onevision

LLaVa_Onevision models for single-image, multi-image, and video scenarios • 9 items • Updated 16 days ago • 11

upvoted a paper 29 days ago

Compositional 3D-aware Video Generation with LLM Director

Paper • 2409.00558 • Published Aug 31 • 14

upvoted 4 collections 30 days ago

Video-LLaVA 1.5 Model

a collection of Video-LLaVA 1.0 • 1 item • Updated Jan 28 • 2

Video-LLaVA 1.0 Model

a collection of Video-LLaVA 1.0 • 3 items • Updated May 23 • 5

LanguageBind 1.5 Model

a collection of LanguageBind based on VIDAL-45M • 2 items • Updated May 23 • 2

LanguageBind 1.0 Model

a collection of LanguageBind based on VIDAL-10M • 9 items • Updated Jan 28 • 4

upvoted a paper 30 days ago

VideoLLaMB: Long-context Video Understanding with Recurrent Memory Bridges

Paper • 2409.01071 • Published Sep 2 • 26

upvoted 3 papers about 1 month ago

ImageInWords: Unlocking Hyper-Detailed Image Descriptions

Paper • 2405.02793 • Published May 5 • 4

OLMoE: Open Mixture-of-Experts Language Models

Paper • 2409.02060 • Published Sep 3 • 76

Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming

Paper • 2408.16725 • Published Aug 29 • 51

upvoted an article about 1 month ago

Article

Fine tuning CLIP with Remote Sensing (Satellite) images and captions

Oct 13, 2021

• 4

upvoted 3 papers about 1 month ago

ReMamba: Equip Mamba with Effective Long-Sequence Modeling

Paper • 2408.15496 • Published Aug 28 • 10

CogVLM2: Visual Language Models for Image and Video Understanding

Paper • 2408.16500 • Published Aug 29 • 56

Law of Vision Representation in MLLMs

Paper • 2408.16357 • Published Aug 29 • 92

upvoted 3 collections about 1 month ago

C4AI Aya 23

Aya 23 is an open weights research release of an instruction fine-tuned model with highly advanced multilingual capabilities. • 4 items • Updated Aug 6 • 45

C4AI Command R

C4AI Command-R is a research release of a 35 billion parameter highly performant generative model. Command-R is a large language model with open weigh • 4 items • Updated Aug 30 • 16

C4AI Command R Plus

C4AI Command R+ is an open weights research release of a 104B billion parameter model with highly advanced capabilities. • 4 items • Updated Aug 30 • 44

upvoted a paper about 1 month ago

LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation

Paper • 2408.15881 • Published Aug 28 • 20