Streamline CUDA-Accelerated Python Install and Packaging Workflows with Wheel Variants
developer.nvidia.com·3d·
Discuss: Hacker News
🔧Systems-level optimizations for LLM serving
Learning to Detect Unknown Jailbreak Attacks in Large Vision-Language Models: A Unified and Accurate Approach
arxiv.org·2d
🧠Large Language Models (LLMs)
Deep Generative Models for Discrete Genotype Simulation
arxiv.org·2d
🔍Retrieval-augmented generation
X-UniMotion: Animating Human Images with Expressive, Unified and Identity-Agnostic Motion Latents
arxiv.org·2d
🔍Retrieval-augmented generation
EntropyGS: An Efficient Entropy Coding on 3D Gaussian Splatting
arxiv.org·1d
🔍Retrieval-augmented generation
Novel View Synthesis with Gaussian Splatting: Impact on Photogrammetry Model Accuracy and Resolution
arxiv.org·4d
🔍Retrieval-augmented generation
MedReasoner: Reinforcement Learning Drives Reasoning Grounding from Clinical Thought to Pixel-Level Precision
arxiv.org·4d
🧠Large Language Models (LLMs)
Physics-Informed Deep Contrast Source Inversion: A Unified Framework for Inverse Scattering Problems
arxiv.org·1d
🔢Quantization of LLMs
Dynamic Uncertainty-aware Multimodal Fusion for Outdoor Health Monitoring
arxiv.org·3d
🧠Large Language Models (LLMs)
Who pays the RENT? Implications of Spatial Inequality for Prediction-Based Allocation Policies
arxiv.org·3d
🤖Agents using LLMs
Chi-Geometry: A Library for Benchmarking Chirality Prediction of GNNs
arxiv.org·3d
📊AI Performance Profiling
Fulfillment of the Work Games: Warehouse Workers' Experiences with Algorithmic Management
arxiv.org·2d
🤖Agents using LLMs
Psyche-R1: Towards Reliable Psychological LLMs through Unified Empathy, Expertise, and Reasoning
arxiv.org·1d
🧠Large Language Models (LLMs)
"I Want My Chart to Be Just for Me": Community-Engaged Design to Support Outpatient Healthcare for Resettled Communities
arxiv.org·1d
🔍Retrieval-augmented generation
Insights from the Algonauts 2025 Winners
arxiv.org·1d
🧠Large Language Models (LLMs)
Energy Experience Design
arxiv.org·5d
🌐Distributed LLM Systems
EvolvR: Self-Evolving Pairwise Reasoning for Story Evaluation to Enhance Generation
arxiv.org·5d
🧠Large Language Models (LLMs)
Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy
arxiv.org·4d
🧠Large Language Models (LLMs)
Multi-head Transformers Provably Learn Symbolic Multi-step Reasoning via Gradient Descent
arxiv.org·4d
📊AI Performance Profiling
Harmonic balance-automatic differentiation method: an out-of-the-box and efficient solver for general nonlinear dynamics simulation
arxiv.org·4d
🔧Systems-level optimizations for LLM serving