Reasoning Beyond Labels: Measuring LLM Sentiment in Low-Resource, Culturally Nuanced Contexts
arxiv.org·2d
🧠Large Language Models (LLMs)
Hacking Hallucinations of MLLMs with Causal Sufficiency and Necessity
arxiv.org·2d
🧠Large Language Models (LLMs)
Resource-Limited Joint Multimodal Sentiment Reasoning and Classification via Chain-of-Thought Enhancement and Distillation
arxiv.org·1d
🧠Large Language Models (LLMs)
Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools
arxiv.org·4d
🤖Agents using LLMs
Whose Truth? Pluralistic Geo-Alignment for (Agentic) AI
arxiv.org·1d
📊AI Performance Profiling
Advanced Hybrid Transformer LSTM Technique with Attention and TS Mixer for Drilling Rate of Penetration Prediction
arxiv.org·1d
⚡Real-time AI Systems
KCR: Resolving Long-Context Knowledge Conflicts via Reasoning in LLMs
arxiv.org·4d
🧠Large Language Models (LLMs)
Telegrapher's Generative Model via Kac Flows
arxiv.org·1d
🧠Large Language Models (LLMs)
From "Aha Moments" to Controllable Thinking: Toward Meta-Cognitive Reasoning in Large Reasoning Models via Decoupled Reasoning and Control
arxiv.org·2d
⚙️AI Infrastructure Automation
Dual Prompt Learning for Adapting Vision-Language Models to Downstream Image-Text Retrieval
arxiv.org·2d
🔍Retrieval-augmented generation
A Foundation Model for DAS Signal Recognition and Visual Prompt Tuning of the Pre-trained Model for Downstream Tasks
arxiv.org·2d
📊AI Performance Profiling
L3M+P: Lifelong Planning with Large Language Models
arxiv.org·4d
🧠Large Language Models (LLMs)
Autonomous Penetration Testing: Solving Capture-the-Flag Challenges with LLMs
arxiv.org·4d
🔧Systems-level optimizations for LLM serving
Modeling Annotator Disagreement with Demographic-Aware Experts and Synthetic Perspectives
arxiv.org·3d
🧠Large Language Models (LLMs)
Derivation and Numerical Simulation of a Thermodynamically Consistent Magneto Two-Phase Flow Model for Magnetic Drug Targeting
arxiv.org·2d
✨Model optimizations in LLMs
PriorRG: Prior-Guided Contrastive Pre-training and Coarse-to-Fine Decoding for Chest X-ray Report Generation
arxiv.org·1d
🔍Retrieval-augmented generation
FairPOT: Balancing AUC Performance and Fairness with Proportional Optimal Transport
arxiv.org·2d
🧠Large Language Models (LLMs)
Compressed Decentralized Momentum Stochastic Gradient Methods for Nonconvex Optimization
arxiv.org·1d
✨Model optimizations in LLMs
Coherent Multimodal Reasoning with Iterative Self-Evaluation for Vision-Language Models
arxiv.org·3d
🧠Large Language Models (LLMs)
How Hackers Exploit AI's Problem-Solving Instincts
developer.nvidia.com·4d
⚙️AI Infrastructure Automation