Pratyay Banerjee

Neilblaze's activity

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

upvoted 10 papers about 22 hours ago

WUSH: Near-Optimal Adaptive Transforms for LLM Quantization

Paper • 2512.00956 • Published 6 days ago • 17

Rectifying LLM Thought from Lens of Optimization

Paper • 2512.01925 • Published 5 days ago • 23

CaptionQA: Is Your Caption as Useful as the Image Itself?

Paper • 2511.21025 • Published 10 days ago • 25

Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models

Paper • 2511.18890 • Published 12 days ago • 29

Guided Self-Evolving LLMs with Minimal Human Supervision

Paper • 2512.02472 • Published 4 days ago • 47

ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration

Paper • 2511.21689 • Published 10 days ago • 94

Stabilizing Reinforcement Learning with LLMs: Formulation and Practices

Paper • 2512.01374 • Published 5 days ago • 76

Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length

Paper • 2512.04677 • Published 2 days ago • 129

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Paper • 2512.02556 • Published 4 days ago • 163

From Code Foundation Models to Agents and Applications: A Practical Guide to Code Intelligence

Paper • 2511.18538 • Published 13 days ago • 238

upvoted a paper 4 days ago

Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B

Paper • 2511.06221 • Published 27 days ago • 128

upvoted a collection 4 days ago

Olmo 3

Collection

Artifacts for the Olmo 3 release. • 9 items • Updated 5 days ago • 140

upvoted an article 4 days ago

view article

Article

Diffusers welcomes FLUX-2

• 
• 
• +6

12 days ago

•

157

upvoted an article 5 days ago

view article

Article

Transformers v5: Simple model definitions powering the AI ecosystem

• 
• 
• +2

6 days ago

•

223

upvoted a collection 5 days ago

The Bestiary

Collection

Decensored language models made using Heretic (https://github.com/p-e-w/heretic) • 6 items • Updated 20 days ago • 68

upvoted 5 papers 8 days ago

GroupRank: A Groupwise Reranking Paradigm Driven by Reinforcement Learning

Paper • 2511.11653 • Published 26 days ago • 54

Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data

Paper • 2511.12609 • Published 20 days ago • 102

Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models

Paper • 2511.08577 • Published 25 days ago • 104

GigaEvo: An Open Source Optimization Framework Powered By LLMs And Evolution Algorithms

Paper • 2511.17592 • Published 19 days ago • 118

One Small Step in Latent, One Giant Leap for Pixels: Fast Latent Upscale Adapter for Your Diffusion Models

Paper • 2511.10629 • Published 23 days ago • 122