Uday Phalak

Uday's activity

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

liked a model about 14 hours ago

bharatgenai/Param-1-2.9B-Instruct

Text Generation • 3B • Updated 4 days ago • 1.38k • 17

upvoted an article about 14 hours ago

view article

Article

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

• 
• 
• +3

7 days ago

•

23

liked a dataset about 15 hours ago

bharatgenai/BhashaBench-Ayur

Viewer • Updated Oct 30, 2025 • 15k • 73 • 9

upvoted 2 papers 7 days ago

PaperBanana: Automating Academic Illustration for AI Scientists

Paper • 2601.23265 • Published 19 days ago • 187

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

Paper • 2602.05027 • Published 14 days ago • 59

upvoted a paper 14 days ago

Shaping capabilities with token-level data filtering

Paper • 2601.21571 • Published 20 days ago • 27

liked a model 18 days ago

meituan-longcat/LongCat-Flash-Lite

Text Generation • Updated 12 days ago • 2.45k • 161

liked a model 20 days ago

moonshotai/Kimi-K2.5

Image-Text-to-Text • 171B • Updated 14 days ago • 895k • • 2.24k

upvoted 3 papers 26 days ago

LLM-in-Sandbox Elicits General Agentic Intelligence

Paper • 2601.16206 • Published 27 days ago • 84

Agentic Reasoning for Large Language Models

Paper • 2601.12538 • Published Jan 18 • 195

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

Paper • 2601.11868 • Published Jan 17 • 32

liked a model 26 days ago

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

Updated 27 days ago • 1.25M • 312

liked a Space 26 days ago

Running on Zero

Featured

1.45k

Qwen3-TTS Demo

🎙

1.45k

Generate speech with custom, cloned, or preset voices

liked a model 27 days ago

nvidia/personaplex-7b-v1

Audio-to-Audio • Updated 3 days ago • 440k • 2.03k

liked a dataset 28 days ago

lu-christina/assistant-axis-vectors

Updated 27 days ago • 312 • 3

upvoted 2 articles 29 days 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

•

106

liked a model about 1 month ago

Lightricks/LTX-2

Image-to-Video • Updated 15 days ago • 2.07M • • 1.55k

upvoted a paper about 1 month ago

LTX-2: Efficient Joint Audio-Visual Foundation Model

Paper • 2601.03233 • Published Jan 6 • 153

liked a Space about 1 month ago

Runtime error

9

MIB Leaderboard

😎

9

Leaderboard for the Mechanistic Interpretability Benchmark