Pratyay Banerjee

Neilblaze's activity

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

upvoted a collection 6 days ago

Qwen3

Collection

27 items • Updated 3 days ago • 510

upvoted an article 7 days ago

view article

Article

Tiny Agents: a MCP-powered agent in 50 lines of code

11 days ago

• 212

upvoted a collection 7 days ago

SVDQuant

Collection

Models and datasets for "SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models" • 20 items • Updated Mar 17 • 34

upvoted 16 papers 7 days ago

70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float

Paper • 2504.11651 • Published 20 days ago • 28

Could Thinking Multilingually Empower LLM Reasoning?

Paper • 2504.11833 • Published 19 days ago • 28

NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodes

Paper • 2504.11544 • Published 20 days ago • 41

Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Paper • 2504.13837 • Published 17 days ago • 118

Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs

Paper • 2504.15280 • Published 14 days ago • 22

FlowReasoner: Reinforcing Query-Level Meta-Agents

Paper • 2504.15257 • Published 14 days ago • 46

Learning to Reason under Off-Policy Guidance

Paper • 2504.14945 • Published 14 days ago • 80

MR. Video: "MapReduce" is the Principle for Long Video Understanding

Paper • 2504.16082 • Published 13 days ago • 6

Progent: Programmable Privilege Control for LLM Agents

Paper • 2504.11703 • Published 19 days ago • 7

From Reflection to Perfection: Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection Tuning

Paper • 2504.16080 • Published 13 days ago • 15

Rethinking the Generation of High-Quality CoT Data from the Perspective of LLM-Adaptive Question Difficulty Grading

Paper • 2504.11919 • Published 19 days ago • 12

Tina: Tiny Reasoning Models via LoRA

Paper • 2504.15777 • Published 13 days ago • 52

VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models

Paper • 2504.15279 • Published 14 days ago • 73

3DV-TON: Textured 3D-Guided Consistent Video Try-on via Diffusion Models

Paper • 2504.17414 • Published 11 days ago • 14

BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs

Paper • 2504.18415 • Published 10 days ago • 41

Towards Understanding Camera Motions in Any Video

Paper • 2504.15376 • Published 14 days ago • 153

upvoted a paper 17 days ago

MCP Safety Audit: LLMs with the Model Context Protocol Allow Major Security Exploits

Paper • 2504.03767 • Published Apr 2 • 3