Andrei Ionescu

a-ionescu's activity

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

upvoted a paper 2 days ago

TAO: Tool-Aware Joint Scheduling for LLM-Based Agentic Serving

Paper • 2610.37230 • Published 6 days ago • 82

upvoted a paper 4 days ago

RoboJev: An Open Vision-Language Judge for Robot Success Detection

Paper • 2610.33718 • Published 9 days ago • 9

upvoted a paper 5 days ago

Function-Space Temporal Self-Distillation for Policy Optimization

Paper • 2610.19687 • Published 19 days ago • 39

upvoted 2 papers 9 days ago

SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes?

Paper • 2610.26659 • Published 14 days ago • 121

Sparsity Should Be ALLOTted by Output: Training-Free Allocation of Block-Sparse Attention for Video Diffusion Transformers

Paper • 2610.29441 • Published 12 days ago • 23

upvoted a paper 11 days ago

RAP: A Dataset for Paper-to-Poster Generation via Declarative Markup from Human-Crafted Exemplars

Paper • 2610.23230 • Published 17 days ago • 36

upvoted a paper 14 days ago

AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards

Paper • 2610.18860 • Published 20 days ago • 45

upvoted 2 papers 20 days ago

UniWAM: Unified World-Action Model

Paper • 2610.02054 • Published Oct 1 • 78

VepAgent: Bridging Causal-Transition via Tool-Augmented Reinforcement Learning for Video Event Prediction

Paper • 2610.06293 • Published 28 days ago • 20

upvoted a paper 25 days ago

On-Policy Parameter Update Direction Underlies Generalization in LLM Post-Training

Paper • 2609.36659 • Published Sep 29 • 31

upvoted 10 papers about 1 month ago

VisionHOPE: Visual Backbones as Self-Modifying Learning Systems

Paper • 2609.33325 • Published Sep 27 • 80

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published Sep 1 • 275

IterSynth: Rethinking Deep Search Agents via Role-Decoupled Iterative Synthesis

Paper • 2609.29444 • Published Sep 24 • 21

Emergent Collusion in Long-Horizon LLM Agent Interaction

Paper • 2609.24967 • Published Sep 21 • 17

Paint-Anything: Unified Any-Color Control for Image Generation and Editing

Paper • 2609.20816 • Published Sep 17 • 51

VākQA: A Benchmark and Evaluation Study for Telugu Spoken Factoid Question Answering

Paper • 2609.19879 • Published Sep 17 • 9

An Empirical Study of Harness Design for Coding Agents

Paper • 2609.20804 • Published Sep 17 • 69

JEPA-Anything: Learning Predictive Models across Different Worlds

Paper • 2609.20800 • Published Sep 17 • 56

LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence

Paper • 2609.17488 • Published Sep 15 • 286

BVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in Blender

Paper • 2609.15478 • Published Sep 14 • 32