World Embedding Benchmark
Paper • 2610.03632 • Published • 51
Dipankar Sarkar PRO
dipankarsarkar
AI & ML interests
Building the AI-native stack. Agents as infrastructure, safety as architecture, performance as plumbing. I publish the receipts: papers, datasets, demos.
Recent Activity
upvoted a paper less than a minute ago
World Embedding Benchmark upvoted a paper 1 minute ago
Multilinguality in Hybrid Attention LLMs upvoted a paper 1 minute ago
Attacca: Goal-Directed Control under State Continuity for Long-Horizon Embodied AgentsOrganizations
upvoted a paper less than a minute ago
upvoted 2
papers 1 minute ago
upvoted 2
papers 2 minutes ago
upvoted a paper 3 minutes ago
upvoted 9
papers about 3 hours ago
HLA: Expressive Hybrid Linear Attention via Chunk-Wise Dynamic Mixing
Paper • 2610.05842 • Published • 5
Collective Bias Mitigation via Model Routing and Collaboration
Paper • 2610.03240 • Published • 18
Capability-Driven Self-Evolution of Agent Memory
Paper • 2610.06361 • Published • 14
UNREAL: Unifying Retrieval and Long-Context with a Single Model
Paper • 2610.08463 • Published • 19
SlimWise: Decoupling Expert Pruning Across Prefill and Decode for Efficient MoE Serving
Paper • 2609.34117 • Published • 10
Stepped MoE: Segment-Level Routing with Configurable Inference Complexity
Paper • 2610.07348 • Published • 2
Towards In-Parameter Memory Augmentation for Large Language Models
Paper • 2610.08630 • Published • 5
Personal-Agent Mediated Recommendation with Cross-Platform User History
Paper • 2610.07588 • Published • 4
MiniCorp: The Last Mile of the AI Agent Firm
Paper • 2610.05912 • Published • 15
upvoted 5
papers about 4 hours ago
DAEDALUS: Bootstrapping Agent Memory from Self-Generated Tasks
Paper • 2610.08048 • Published • 8
Harness Engineering for Software Engineering via Modular Executable Dev-Primitives
Paper • 2610.07832 • Published • 5
EVISKILL: Grounding Skill Evolution in Replayable Evidence
Paper • 2610.05030 • Published • 36
Harness-Aware Distillation for Small Language Model Agents
Paper • 2610.02858 • Published • 5
AGO AI Quality Gate: Evidence-First Release Decisions for Retrieval-Augmented Generation
Paper • 2610.01218 • Published • 16