Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining
Paper • 2605.14747 • Published • 139 •
3
Avi
avahal
AI & ML interests
LLMs
Recent Activity
commentedon a paper about 11 hours ago
Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining commentedon a paper about 11 hours ago
Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation commentedon a paper about 11 hours ago
Active Learners as Efficient PRP RerankersOrganizations
None yet
commented 5
papers about 11 hours ago
Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation
Paper • 2605.19833 • Published • 118 •
2
Active Learners as Efficient PRP Rerankers
Paper • 2605.14236 • Published • 91 •
4
When Vision Speaks for Sound
Paper • 2605.16403 • Published • 94 •
2
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information
Paper • 2605.11609 • Published • 135 •
4
commented 4
papers about 13 hours ago
LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation
Paper • 2605.18739 • Published • 104 •
2
MMSkills: Towards Multimodal Skills for General Visual Agents
Paper • 2605.13527 • Published • 116 •
3
PhysBrain 1.0 Technical Report
Paper • 2605.15298 • Published • 138 •
2
CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence
Paper • 2605.12882 • Published • 261 •
3
commented 5
papers about 14 hours ago
EVA-Bench: A New End-to-end Framework for Evaluating Voice Agents
Paper • 2605.13841 • Published • 64 •
3
Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context
Paper • 2605.13831 • Published • 85 •
2
AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
Paper • 2605.13724 • Published • 96 •
2
MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image
Paper • 2605.10616 • Published • 138 •
3
MinT: Managed Infrastructure for Training and Serving Millions of LLMs
Paper • 2605.13779 • Published • 216 •
4
commented 6
papers 1 day ago
World Action Models: The Next Frontier in Embodied AI
Paper • 2605.12090 • Published • 64 •
2
RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards
Paper • 2605.10899 • Published • 74 •
2
$δ$-mem: Efficient Online Memory for Large Language Models
Paper • 2605.12357 • Published • 120 •
5
MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents
Paper • 2605.09530 • Published • 145 •
4
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
Paper • 2605.12500 • Published • 185 •
2
TMAS: Scaling Test-Time Compute via Multi-Agent Synergy
Paper • 2605.10344 • Published • 49 •
2