SAMBIT CHAKRABORTY

sambitchakhf03's activity

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

upvoted a paper about 16 hours ago

NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models

Paper • 2602.06694 • Published 6 days ago • 12

upvoted a paper 1 day ago

OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration

Paper • 2602.05400 • Published 8 days ago • 294

upvoted 2 papers 2 days ago

AudioSAE: Towards Understanding of Audio-Processing Models with Sparse AutoEncoders

Paper • 2602.05027 • Published 8 days ago • 59

Steering LLMs via Scalable Interactive Oversight

Paper • 2602.04210 • Published 9 days ago • 18

upvoted 2 papers 4 days ago

Reinforced Attention Learning

Paper • 2602.04884 • Published 8 days ago • 27

DFlash: Block Diffusion for Flash Speculative Decoding

Paper • 2602.06036 • Published 7 days ago • 40

upvoted 2 papers 7 days ago

OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models

Paper • 2602.04804 • Published 8 days ago • 46

Self-Hinting Language Models Enhance Reinforcement Learning

Paper • 2602.03143 • Published 10 days ago • 27

upvoted 3 papers 8 days ago

Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text

Paper • 2601.22975 • Published 13 days ago • 96

PixelGen: Pixel Diffusion Beats Latent Diffusion with Perceptual Loss

Paper • 2602.02493 • Published 10 days ago • 41

ReGuLaR: Variational Latent Reasoning Guided by Rendered Chain-of-Thought

Paper • 2601.23184 • Published 13 days ago • 35

upvoted 2 papers 10 days ago

Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation

Paper • 2601.22813 • Published 13 days ago • 55

ConceptMoE: Adaptive Token-to-Concept Compression for Implicit Compute Allocation

Paper • 2601.21420 • Published 14 days ago • 42

upvoted a paper 11 days ago

Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability

Paper • 2601.18778 • Published 17 days ago • 40

upvoted 2 papers 13 days ago

Self-Improving Pretraining: using post-trained models to pretrain better models

Paper • 2601.21343 • Published 15 days ago • 16

Post-LayerNorm Is Back: Stable, ExpressivE, and Deep

Paper • 2601.19895 • Published 16 days ago • 23

upvoted a paper 16 days ago

Endless Terminals: Scaling RL Environments for Terminal Agents

Paper • 2601.16443 • Published 21 days ago • 16

upvoted 2 papers 17 days ago

VisGym: Diverse, Customizable, Scalable Environments for Multimodal Agents

Paper • 2601.16973 • Published 20 days ago • 40

LongCat-Flash-Thinking-2601 Technical Report

Paper • 2601.16725 • Published 20 days ago • 175

upvoted a paper 18 days ago

Agentic Reasoning for Large Language Models

Paper • 2601.12538 • Published 25 days ago • 195