Omni-Embed-Mini: Binding Modalities Without Forgetting via Dense Distillation
Paper • 2610.02148 • Published • 15 •
2
Librarian Bot (Bot)
librarian-bot
AI & ML interests
I am a friendly librarian bot working to help improve metadata on the 🤗 hub. Run by Hugging Face'ss Machine Learning Librarian (HF username: davanstrien)
Recent Activity
commentedon a paper about 3 hours ago
Omni-Embed-Mini: Binding Modalities Without Forgetting via Dense Distillation commentedon a paper about 3 hours ago
When Users Change Their Minds: Measuring and Repairing Intent Drift in LLM Agents commentedon a paper about 3 hours ago
Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success Rate but 65% Fewer TokensOrganizations
commented 20
papers about 3 hours ago
When Users Change Their Minds: Measuring and Repairing Intent Drift in LLM Agents
Paper • 2609.32520 • Published • 11 •
2
Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success Rate but 65% Fewer Tokens
Paper • 2610.01939 • Published • 26 •
2
ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization
Paper • 2610.00906 • Published • 50 •
2
It Takes Workflows to Evolve Better Workflows
Paper • 2610.01026 • Published • 3 •
2
LOCI: Spatial Linear Memory for Streaming World Models
Paper • 2609.40222 • Published • 6 •
2
GraphForge: Training Working Agents with Graph-Anchored Workspace Synthesis
Paper • 2609.38923 • Published • 34 •
2
DexPolicy: Scheduled Exploration for Trajectory-Guided Dexterous Manipulation
Paper • 2610.00360 • Published • 2 •
2
DataMagic: Authoring Data Videos through Declarative Multi-Agent Orchestration
Paper • 2609.33403 • Published • 6 •
2
Replacing Large Language Models with Jev Decision Models for Low-Latency Edge Service Orchestration
Paper • 2609.22753 • Published • 1 •
2
CorrGRPO: Correlation-Normalized GRPO for Multi-Reward Learning
Paper • 2609.36820 • Published • 18 •
2
Decoding Looped Transformers Better for (Almost) Free
Paper • 2610.02185 • Published • 19 •
2
Explore Broadly, Reason Sharply: Push Small Models toward the Frontier via Sampling
Paper • 2609.38104 • Published • 2 •
2
PhysVista: Benchmarking Physical Intelligence in VLMs via a Perception-Reasoning-Assessment Loop
Paper • 2610.00559 • Published • 14 •
2
Pretrain Once, Route Anywhere: Towards a Foundation Model for LLM Routing
Paper • 2609.37362 • Published • 9 •
2
Architect-Ant: Editable Automatic Furnishing of Architectural Floor Plans
Paper • 2606.10953 • Published • 17 •
2
Pay for the Fault, Not the Flow: Label-Free In-Flow Multi-Agent Workflow Optimization
Paper • 2610.01017 • Published • 2 •
2
Sharpening Tax in Post-Training
Paper • 2610.01509 • Published • 66 •
2
AgSpec: Pushing the Limits of Retrieval-Based Speculative Decoding in Coding Agent Pipelines
Paper • 2610.01108 • Published • 7 •
2
Devils in Question Relay: Source-Conditioned Relay Steering to Mitigate Hallucinations in Audio-visual Large Language Models
Paper • 2609.37568 • Published • 5 •
2