VeS: Teaching Pixels to Listen Without Supervision
arxiv.org·5d
🧠Large Language Models (LLMs)
Organic Electrochemical Neurons: Nonlinear Tools for Complex Dynamics
arxiv.org·13h
⚡Real-time AI Systems
StaffPro: an LLM Agent for Joint Staffing and Profiling
arxiv.org·5d
🤖Agents using LLMs
Probabilistic Directed Distance Fields for Ray-Based Shape Representations
arxiv.org·5d
📊AI Performance Profiling
Adversarial-Guided Diffusion for Multimodal LLM Attacks
arxiv.org·3d
🧠Large Language Models (LLMs)
Learning Only with Images: Visual Reinforcement Learning with Reasoning, Rendering, and Visual Feedback
arxiv.org·6d
🧠Large Language Models (LLMs)
Towards Interpretable Renal Health Decline Forecasting via Multi-LMM Collaborative Reasoning Framework
arxiv.org·4d
🧠Large Language Models (LLMs)
Opacity as Authority: Arbitrariness and the Preclusion of Contestation
arxiv.org·3d
💬Prompt optimizations for LLM serving
ReGATE: Learning Faster and Better with Fewer Tokens in MLLMs
arxiv.org·5d
🧠Large Language Models (LLMs)
LVM-GP: Uncertainty-Aware PDE Solver via coupling latent variable model and Gaussian process
arxiv.org·4d
🧠Large Language Models (LLMs)
MAGE: Multimodal Alignment and Generation Enhancement via Bridging Visual and Semantic Spaces
arxiv.org·5d
🧠Large Language Models (LLMs)
AoI-Aware Resource Allocation with Deep Reinforcement Learning for HAPS-V2X Networks
arxiv.org·13h
🔧Systems-level optimizations for LLM serving
UloRL:An Ultra-Long Output Reinforcement Learning Approach for Advancing Large Language Models' Reasoning Abilities
arxiv.org·6d
🧠Large Language Models (LLMs)
Dark Side of Modalities: Reinforced Multimodal Distillation for Multimodal Knowledge Graph Reasoning
arxiv.org·6d
🧠Large Language Models (LLMs)
Progressive Homeostatic and Plastic Prompt Tuning for Audio-Visual Multi-Task Incremental Learning
arxiv.org·5d
⚡Real-time AI Systems
Moravec's Paradox: Towards an Auditory Turing Test
arxiv.org·3d·
Discuss: Hacker News
🧠Large Language Models (LLMs)
The Effect of Prior Parameters on Standardized Kalman Filter-Based EEG Source Localization
arxiv.org·3d
🔢Quantization of LLMs
MIMII-Agent: Leveraging LLMs with Function Calling for Relative Evaluation of Anomalous Sound Detection
arxiv.org·6d
🧠Large Language Models (LLMs)
AutoTIR: Autonomous Tools Integrated Reasoning via Reinforcement Learning
arxiv.org·5d
🧠Large Language Models (LLMs)
TempRe: Template generation for single and direct multi-step retrosynthesis
arxiv.org·5d
💬Prompt optimizations for LLM serving