Article
Native-speed vLLM transformers modeling backend
hmellor, lysandre
• • 24
Gibran Iqbal
Jibbscript
AI & ML interests
None yet
Recent Activity
liked a dataset about 1 hour ago
piimb/pii-masking-benchmark liked a model about 2 hours ago
OpenMed/privacy-filter-multilingual-v2-mlx-8bit liked a model about 2 hours ago
OpenMed/privacy-filter-multilingual-v2-mlxOrganizations
upvoted an article about 16 hours ago
upvoted a collection 4 days ago
upvoted a paper 4 days ago
upvoted 13
papers 6 days ago
Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads
Paper • 2607.01002 • Published • 18
Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning
Paper • 2606.31825 • Published • 26
SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use
Paper • 2607.01874 • Published • 18
WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory
Paper • 2607.02517 • Published • 32
AgenticDataBench: A Comprehensive Benchmark for Data Agents
Paper • 2607.01647 • Published • 35
Morphing into Hybrid Attention Models
Paper • 2606.30562 • Published • 47
EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments
Paper • 2607.02440 • Published • 50
AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents
Paper • 2607.02255 • Published • 60
Program-as-Weights: A Programming Paradigm for Fuzzy Functions
Paper • 2607.02512 • Published • 118
Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity
Paper • 2607.00248 • Published • 28
CausalMix: Data Mixture as Causal Inference for Language Model Training
Paper • 2607.01104 • Published • 19
ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving
Paper • 2607.00466 • Published • 31
MemSyco-Bench: Benchmarking Sycophancy in Agent Memory
Paper • 2607.01071 • Published • 29
upvoted 2
papers 8 days ago
upvoted 2
papers 13 days ago