Pratyay Banerjee

Neilblaze's activity

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

upvoted a collection 3 days ago

Instella ✨

Collection

Announcing Instella, a series of 3 billion parameter language models developed by AMD, trained from scratch on 128 Instinct MI300X GPUs. • 5 items • Updated 23 days ago • 7

upvoted 15 papers 3 days ago

Temporal Consistency for LLM Reasoning Process Error Identification

Paper • 2503.14495 • Published 10 days ago • 9

CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era

Paper • 2503.12329 • Published 13 days ago • 24

DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Paper • 2503.14476 • Published 10 days ago • 108

Impossible Videos

Paper • 2503.14378 • Published 11 days ago • 54

MathFusion: Enhancing Mathematic Problem-solving of LLM through Instruction Fusion

Paper • 2503.16212 • Published 9 days ago • 22

LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds

Paper • 2503.10625 • Published 15 days ago • 26

Why Do Multi-Agent LLM Systems Fail?

Paper • 2503.13657 • Published 11 days ago • 41

Inside-Out: Hidden Factual Knowledge in LLMs

Paper • 2503.15299 • Published 10 days ago • 40

One-Step Residual Shifting Diffusion for Image Super-Resolution via Distillation

Paper • 2503.13358 • Published 12 days ago • 90

Lost in Cultural Translation: Do LLMs Struggle with Math Across Cultural Contexts?

Paper • 2503.18018 • Published 6 days ago • 5

Typed-RAG: Type-aware Multi-Aspect Decomposition for Non-Factoid Question Answering

Paper • 2503.15879 • Published 9 days ago • 6

Video SimpleQA: Towards Factuality Evaluation in Large Video Language Models

Paper • 2503.18923 • Published 4 days ago • 11

AgentRxiv: Towards Collaborative Autonomous Research

Paper • 2503.18102 • Published 6 days ago • 20

Judge Anything: MLLM as a Judge Across Any Modality

Paper • 2503.17489 • Published 7 days ago • 19

I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders

Paper • 2503.18878 • Published 5 days ago • 108

upvoted a paper 6 days ago

SPIN-Bench: How Well Do LLMs Plan Strategically and Reason Socially?

Paper • 2503.12349 • Published 13 days ago • 40

upvoted a paper 7 days ago

Survey on Evaluation of LLM-based Agents

Paper • 2503.16416 • Published 8 days ago • 79

upvoted 2 papers 15 days ago

Token-Efficient Long Video Understanding for Multimodal LLMs

Paper • 2503.04130 • Published 23 days ago • 86

SAGE: A Framework of Precise Retrieval for RAG

Paper • 2503.01713 • Published 26 days ago • 5