Reza Sayar PRO

Reza2kn's activity

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

upvoted a collection 10 days ago

RE-USE

Collection

Multilingual Universal Speech Enhancement • 8 items • Updated about 11 hours ago • 8

upvoted a paper 12 days ago

What Effort Level Should I Choose? On the Economics of Reasoning Effort in LLM Agents

Paper • 2610.34491 • Published 20 days ago • 22

upvoted a paper 21 days ago

MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction

Paper • 2604.27393 • Published Apr 30 • 70

upvoted a collection 26 days ago

Building Better Activation Oracles

Collection

Models and Datasets from Building Better Activation Oracles • 8 items • Updated Sep 1 • 2

upvoted 9 papers 27 days ago

3DCodeVerse: Exploring 3D Worlds as Code

Paper • 2610.22341 • Published 30 days ago • 63

Multics: Generative Multi-Player World Model with Hierarchical Communication

Paper • 2610.17201 • Published Oct 12 • 57

UltraBERT: Beyond the Limit of BERT Pre-Training

Paper • 2610.15028 • Published Oct 10 • 63

VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs

Paper • 2610.07987 • Published Oct 6 • 59

Towards Agentic Robots: Model, Data, Environment, and Harness

Paper • 2610.20442 • Published about 1 month ago • 33

CineRecon: Benchmarking Frontier Models for Agentic Cinematic Reconstruction

Paper • 2610.16577 • Published Oct 12 • 23

RoTA-Bench: Evaluating 3D Spatial Reasoning through Interactive Projection Alignment

Paper • 2610.17665 • Published about 1 month ago • 55

GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed

Paper • 2609.39600 • Published Sep 30 • 34

GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives

Paper • 2609.39601 • Published Sep 30 • 93

upvoted an article about 2 months ago

view article

Article

YODAS v3: A 1 Million Hour Dataset for the Next Generation of Open Voice AI Research

• 

espnet

•

Sep 27

• 37

upvoted a collection about 2 months ago

GLiNER2.5 Models

Collection

6 items • Updated Sep 24 • 44

upvoted 3 collections 2 months ago

RLDX-1

Collection

RLDX-1 : General-purpose robotics foundation model for dexterous manipulation. • 12 items • Updated 2 days ago • 28

NeoMME

Collection

Meet NeoMME: a family of 260M and 800M Multimodal-Native Multilingual Encoders • 12 items • Updated Sep 28 • 33

Spark-X2.5

Collection

Spark-X2.5 is a compact, general-purpose language model for conversation, writing, translation, reasoning, coding, tool use, and agentic workflows. • 10 items • Updated Sep 16 • 51

upvoted a paper 3 months ago

Procedura: Agentic 3D Modeling with Procedural Control

Paper • 2608.26238 • Published Aug 26 • 17

upvoted a collection 3 months ago

EgoSuite-Open100K

Collection

The largest fully-annotated open egocentric human dataset. 100,000 hours across 15,000+ tasks and scenes. • 3 items • Updated Aug 19 • 124