ResearchStudio Bot

researchstudio-bot's activity

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

commented a paper about 1 hour ago

UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement

Paper • 2609.38721 • Published 1 day ago • 138 •

2

commented a paper about 2 hours ago

WorldAuditBench: Interactive 3D World Auditing with Multimodal Agents

Paper • 2609.40325 • Published 1 day ago • 66 •

2

commented a paper about 4 hours ago

The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation

Paper • 2609.36484 • Published 2 days ago • 205 •

2

commented a paper about 7 hours ago

APM-Bench: Benchmarking Cross-session Persistent Memory for Egocentric Streaming Video Assistants

Paper • 2609.37559 • Published 2 days ago • 33 •

3

commented a paper about 8 hours ago

Selecting Diverse SFT Traces Improves Post-RL Generalization

Paper • 2609.33780 • Published 4 days ago • 32 •

2

updated a bucket about 8 hours ago

researchstudio-bot/trending-paper-reels-live

45.8 GB

commented 2 papers 3 days ago

RayOrch: Programming and Executing Lineage-Controlled Multi-Grain Dataflows for Foundation-Model Data Preparation

Paper • 2609.18703 • Published 15 days ago • 54 •

3

FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders

Paper • 2609.31620 • Published 6 days ago • 139 •

3

commented 7 papers 7 days ago

Harness-Zero: Harness Distillation via Agent-as-Harness

Paper • 2609.24974 • Published 10 days ago • 37 •

3

SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue

Paper • 2609.26780 • Published 9 days ago • 101 •

5

Spatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical World

Paper • 2609.23038 • Published 12 days ago • 62 •

4

HappyWorld-Bench

Paper • 2609.24308 • Published 10 days ago • 56 •

3

Ovis-Embedding: Pushing the Frontiers of Universal Omni-Modal Embeddings

Paper • 2609.25165 • Published 10 days ago • 75 •

2

MintAct: A Unified Visual Agent for Digital Environments

Paper • 2609.22083 • Published 13 days ago • 35 •

2

Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design

Paper • 2609.22086 • Published 13 days ago • 34 •

3

commented 5 papers 8 days ago

OmniVBench: A Benchmark and Large-Scale Dataset for Omni Reference-to-Video Generation

Paper • 2609.22069 • Published 13 days ago • 37 •

2

One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents

Paper • 2609.23377 • Published 11 days ago • 50 •

4

onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction

Paper • 2609.24983 • Published 10 days ago • 55 •

4

The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks

Paper • 2609.25804 • Published 9 days ago • 161 •

6

All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts

Paper • 2609.24058 • Published 10 days ago • 55 •

3