Vivaan Malhotra

vivaan-mal's activity

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

upvoted 3 papers about 10 hours ago

More Memory, Worse Agents: Error Reproduction and Anti-Persistence in LLM Agents

Paper • 2610.27406 • Published 4 days ago • 14

Large Flow Language Models

Paper • 2610.28559 • Published 3 days ago • 20

CoEvo-RSI: When Harnesses Evolve, Which Models Should Follow?

Paper • 2610.25078 • Published 5 days ago • 119

upvoted 2 papers 1 day ago

OPMD: On-Policy Mechanism Distillation Beyond Output Supervision

Paper • 2610.14022 • Published 24 days ago • 18

HexaShell: A Thin Harness for Exploring the Limits of VLM Agents as Robot Coding Agents

Paper • 2610.23479 • Published 7 days ago • 119

upvoted 10 papers 3 days ago

Velox: Spatial Memory Makes World Models Efficient

Paper • 2610.22311 • Published 8 days ago • 32

Beyond Policy Rollouts: Embedding-Space Directional Exploration with Anchored Noise for LLM RLVR

Paper • 2610.16105 • Published 11 days ago • 16

Learning Where to Split: Dynamic Band Splitting for Audio Source Separation

Paper • 2610.14993 • Published 13 days ago • 62

Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation

Paper • 2610.21601 • Published 8 days ago • 220

OmniVerifier-C1: Decomposed Graded Verifier for Rule-Governed Generative World Modeling

Paper • 2610.22355 • Published 8 days ago • 44

Are We Testing Too Much? A Survey of Benchmark Compression for Efficient Evaluation of Large Language Models

Paper • 2610.18248 • Published 10 days ago • 19

Player-1: Learning to Play from Synthetic Experience

Paper • 2610.20584 • Published 9 days ago • 351

RAR: Rate-Adaptive Rollout for Time-Consistent Interactive World Models

Paper • 2610.16302 • Published 11 days ago • 21

LatentLoop: Scaling Looped MoE Models with Asymmetric Compute Allocation

Paper • 2610.19975 • Published 9 days ago • 82

LensErase: A Foundation Model for Erase Anything

Paper • 2610.18072 • Published 10 days ago • 52

upvoted 5 papers 5 days ago

Chaos in the Text: Revealing the Modality Preference in Mixed-Modality Retrievers

Paper • 2610.11816 • Published 15 days ago • 23

Relevance Does Not Imply Applicability: Experience Activation for Personal GUI Agents

Paper • 2609.33304 • Published 26 days ago • 25

Less from More: Reinforcing Sparse Video Reasoning from Dense References

Paper • 2610.10893 • Published 16 days ago • 13

Jeva: System One Models from First Principles

Paper • 2610.18773 • Published 10 days ago • 396

ExeWorldBench: Benchmarking Code-Based Executable 3D World Modeling

Paper • 2610.15166 • Published 13 days ago • 85