Reza Sayar's picture

Reza Sayar PRO

Reza2kn

·

AI & ML interests

None yet

Recent Activity

liked a dataset about 6 hours ago

homebrewltd/Maze-Reasoning-GRPO-v0.1

liked a dataset about 6 hours ago

homebrewltd/Maze-Reasoning-Reset-v0.1

liked a dataset about 6 hours ago

homebrewltd/Maze-Bench-v0.2

View all activity

Organizations

Reza2kn's activity

upvoted 2 papers about 22 hours ago

REALTALK: A 21-Day Real-World Dataset for Long-Term Conversation

Paper • 2502.13270 • Published 3 days ago • 3

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

Paper • 2502.14739 • Published 1 day ago • 81

upvoted a paper about 23 hours ago

YOLOv12: Attention-Centric Real-Time Object Detectors

Paper • 2502.12524 • Published 4 days ago • 7

upvoted 2 collections 2 days ago

Paligemma 2

25 items • Updated 2 days ago • 1

PaliGemma 2 Mix

13 items • Updated 2 days ago • 51

upvoted an article 3 days ago

Article

Mixture of Tunable Experts - Behavior Modification of DeepSeek-R1 at Inference Time

By

and 4 others •

3 days ago

• 19

upvoted 2 papers 3 days ago

Small Models, Big Impact: Efficient Corpus and Graph-Based Adaptation of Small Multilingual Language Models for Low-Resource Languages

Paper • 2502.10140 • Published 8 days ago • 9

Can a Single Model Master Both Multi-turn Conversations and Tool Use? CALM: A Unified Conversational Agentic Language Model

Paper • 2502.08820 • Published 9 days ago • 4

upvoted a collection 3 days ago

Domain Classifiers

4 items • Updated 10 days ago • 2

upvoted a collection 4 days ago

Tiny-Agent-a

fast and powerful agentic models designed to run on edge devices. • 6 items • Updated 10 days ago • 7

upvoted 4 papers 6 days ago

InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU

Paper • 2502.08910 • Published 9 days ago • 139

CoSER: Coordinating LLM-Based Persona Simulation of Established Roles

Paper • 2502.09082 • Published 9 days ago • 27

MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency

Paper • 2502.09621 • Published 8 days ago • 27

CoT-Valve: Length-Compressible Chain-of-Thought Tuning

Paper • 2502.09601 • Published 8 days ago • 12

upvoted a collection 6 days ago

CoT-Valve

5 items • Updated 8 days ago • 1

upvoted a collection 7 days ago

Ultravox v0.5

Ultravox is a multimodal Speech LLM built around different pretrained LLMs (frozen) and the whisper-large-v3-turbo (fine-tuned) backbone. • 3 items • Updated 11 days ago • 5

upvoted a paper 8 days ago

TransMLA: Multi-head Latent Attention Is All You Need

Paper • 2502.07864 • Published 10 days ago • 43

upvoted a collection 8 days ago

BenchMAX

10 items • Updated 11 days ago • 4

upvoted 2 papers 8 days ago

Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey

Paper • 2502.06872 • Published 14 days ago • 8

NoLiMa: Long-Context Evaluation Beyond Literal Matching

Paper • 2502.05167 • Published 14 days ago • 15