Priya Nair

pnair-iisc's activity

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

upvoted a paper 6 days ago

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

Paper • 2610.27406 • Published 10 days ago • 17

upvoted 2 papers 10 days ago

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

Paper • 2610.20442 • Published 15 days ago • 43

SWE-MISBEHAVIOR: Benchmarking and Mitigating Boundary Violations in Software Coding Agents

Paper • 2610.18206 • Published 16 days ago • 19

upvoted a paper 12 days ago

VideoJev: System One Model for Video Understanding and Interaction

Paper • 2610.18615 • Published 16 days ago • 344

upvoted a paper 18 days ago

DuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation

Paper • 2610.03543 • Published 27 days ago • 103

upvoted a paper 22 days ago

Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs

Paper • 2609.32259 • Published 30 days ago • 104

upvoted 2 papers 26 days ago

When Does Dense Retrieval Need Asymmetric Geometry? A Bias-Variance Theory of Shared and Dual Projections

Paper • 2609.32488 • Published Sep 26 • 27

FocusVTC: Efficient and High-Performance Visual Text Compression with Adaptive Resolution

Paper • 2609.36651 • Published 30 days ago • 34

upvoted a paper 29 days ago

Neural Spectral Capacity: Measuring and Designing Architectures from Network Specification Alone

Paper • 2609.23087 • Published Sep 19 • 11

upvoted 11 papers about 1 month ago

Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents

Paper • 2609.27334 • Published Sep 23 • 57

RULER: Instance-aware Rubric Rewards for SVG Generation

Paper • 2609.25270 • Published Sep 21 • 106

HuRo: Robotizing Human Videos for Scalable VLA Pretraining

Paper • 2609.10706 • Published Sep 18 • 30

Grounded Skill Synthesis from Code at Scale for Agentic Intelligence

Paper • 2609.05571 • Published Sep 4 • 119

When2Think: Learning When and How Much to Reason

Paper • 2609.19671 • Published about 1 month ago • 55

SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness

Paper • 2609.20519 • Published Sep 17 • 142

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published Sep 1 • 535

ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments

Paper • 2609.19134 • Published Sep 16 • 106

Show-Harness: Just a VLM Agent Can Play Robots

Paper • 2609.10522 • Published Sep 9 • 109

The Router Within: Eliciting Native Skill Routing from a Frozen LLM

Paper • 2609.15982 • Published Sep 14 • 8

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Paper • 2609.06986 • Published Sep 7 • 371