CLEAR: Continuous Latent Adapter Routing for Utility-Preserving LLM Safety Alignment
Paper • 2608.21278 • Published • 5 •
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 21 hours ago
CLEAR: Continuous Latent Adapter Routing for Utility-Preserving LLM Safety Alignment commentedon a paper about 21 hours ago
Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models commentedon a paper about 21 hours ago
Daedalus-150M: A Convolution-Attention Hybrid Designed for CPU InferenceOrganizations
commented 20
papers about 21 hours ago
Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models
Paper • 2608.16647 • Published • 15 •
2
Daedalus-150M: A Convolution-Attention Hybrid Designed for CPU Inference
Paper • 2608.20210 • Published • 7 •
4
Let's Scale Step by Step: Compute-Efficient Hyperparameter Transfer for Large-Scale Mixture-of-Experts
Paper • 2608.20061 • Published • 38 •
2
Human-Centric Intelligence in the Era of Foundation Models: A Survey
Paper • 2608.18184 • Published • 5 •
2
Hadith computational science in the age of large language models: a critical narrative review
Paper • 2608.20364 • Published • 2 •
2
EviRank: Structured Relevance Evidence for Multimodal Image Re-ranking
Paper • 2608.20886 • Published • 11 •
2
Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs
Paper • 2608.12781 • Published • 30 •
4
AgentMercury: Your Agent Can Synthesize Verifiable Environments for Business Scenarios at scale
Paper • 2608.20634 • Published • 9 •
3
FlavourBench: Ranking Frontier Language Models with Executable Culinary Ground Truth
Paper • 2608.20574 • Published • 3 •
2
Llama-Mobile: Efficient 2.7-Bit Quantization of VLMs
Paper • 2608.21134 • Published • 6 •
1
Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence
Paper • 2608.21156 • Published • 46 •
2
OmniAssistBench: Assistant-style Interaction Benchmark for Omni-LLMs
Paper • 2608.21360 • Published • 28 •
2
InfinityEdit: Infinite Video Editing with a Lightweight Edit-Ignition Adapter
Paper • 2608.20910 • Published • 35 •
1
ParaTempo: Efficient Parallel Reasoning via Temporal Confidence
Paper • 2608.16425 • Published • 32 •
3
Partition the Support, Reconstruct the Residual: Training-Free Sparse Attention for Video Generation and World Models
Paper • 2608.18484 • Published • 8 •
4
UniSpace: Unified Visual Representation and Scalable Multimodal Modeling
Paper • 2608.08676 • Published • 10 •
2
PhysCaP: Grounding Code-as-Policy Agent with Physics-Informed Exploration
Paper • 2608.21031 • Published • 3 •
2
Peer-Voted LLM-Agent Stress Tests Find Feed-Induced Lexical Convergence but No Reliable Matched-Exposure Advantage for Distributed Sources
Paper • 2608.20438 • Published • 3 •
2
Towards Faithful Simulation of Human Shopping Behavior
Paper • 2608.20707 • Published • 5 •
2