Uday Phalak

Uday's activity

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

liked a model 9 days ago

bharatgenai/Param-1-2.9B-Instruct

Text Generation • 3B • Updated 2 days ago • 2k • 17

upvoted an article 9 days ago

view article

Article

OpenEnv in Practice: Evaluating Tool-Using Agents in Real-World Environments

• 
• 
• +3

15 days ago

•

30

liked a dataset 9 days ago

bharatgenai/BhashaBench-Ayur

Viewer • Updated Oct 30, 2025 • 15k • 120 • 9

upvoted 2 papers 15 days ago

PaperBanana: Automating Academic Illustration for AI Scientists

Paper • 2601.23265 • Published 27 days ago • 200

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

Paper • 2602.05027 • Published 22 days ago • 60

upvoted a paper 22 days ago

Shaping capabilities with token-level data filtering

Paper • 2601.21571 • Published 28 days ago • 27

liked a model 26 days ago

meituan-longcat/LongCat-Flash-Lite

Text Generation • Updated 20 days ago • 2.96k • 168

liked a model 28 days ago

moonshotai/Kimi-K2.5

Image-Text-to-Text • 171B • Updated 22 days ago • 1.48M • • 2.17k

upvoted 3 papers about 1 month ago

LLM-in-Sandbox Elicits General Agentic Intelligence

Paper • 2601.16206 • Published Jan 22 • 84

Agentic Reasoning for Large Language Models

Paper • 2601.12538 • Published Jan 18 • 197

Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces

Paper • 2601.11868 • Published Jan 17 • 34

liked a model about 1 month ago

Qwen/Qwen3-TTS-12Hz-1.7B-Base

Updated Jan 23 • 1.86M • 324

liked a Space about 1 month ago

Running on Zero

Featured

1.56k

Qwen3-TTS Demo

🎙

1.56k

Generate custom speech from text, voice descriptions, or samples

liked a model about 1 month ago

nvidia/personaplex-7b-v1

Audio-to-Audio • Updated 11 days ago • 545k • 2.21k

liked a dataset about 1 month ago

lu-christina/assistant-axis-vectors

Updated Jan 22 • 358 • 3

upvoted 2 articles about 1 month ago

view article

Article

SmolLM-Smashed: Tiny Giants, Optimized for Speed

• 

Jan 13

•

14

view article

Article

Open Responses: What you need to know

• 
• 
• +2

Jan 15

•

108

liked a model about 1 month ago

Lightricks/LTX-2

Image-to-Video • Updated 2 days ago • 1.88M • • 1.58k

upvoted a paper about 1 month ago

LTX-2: Efficient Joint Audio-Visual Foundation Model

Paper • 2601.03233 • Published Jan 6 • 154

liked a Space about 2 months ago

Running

9

MIB Leaderboard

😎

9

Leaderboard for the Mechanistic Interpretability Benchmark