Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following
arxiv.org·6d
🧠Large Language Models (LLMs)
Estimating Worst-Case Frontier Risks of Open-Weight LLMs
arxiv.org·6d
🔧Systems-level optimizations for LLM serving
Boosting Visual Knowledge-Intensive Training for LVLMs Through Causality-Driven Visual Object Completion
arxiv.org·5d
🧠Large Language Models (LLMs)
DART: Dual Adaptive Refinement Transfer for Open-Vocabulary Multi-Label Recognition
arxiv.org·4d
🧠Large Language Models (LLMs)
Reconstruction of Solar EUV Irradiance Using CaII K Images and SOHO/SEM Data with Bayesian Deep Learning and Uncertainty Quantification
arxiv.org·4h
⚙️AI Infrastructure Automation
Epidemic Control on a Large-Scale-Agent-Based Epidemiology Model using Deep Deterministic Policy Gradient
arxiv.org·1d
⚡Real-time AI Systems
SLIP: Soft Label Mechanism and Key-Extraction-Guided CoT-based Defense Against Instruction Backdoor in APIs
arxiv.org·1d
💬Prompt optimizations for LLM serving
Topology Generation of UAV Covert Communication Networks: A Graph Diffusion Approach with Incentive Mechanism
arxiv.org·4h
🤖Agents using LLMs
FS-IQA: Certified Feature Smoothing for Robust Image Quality Assessment
arxiv.org·4d
📊AI Performance Profiling
Interpretable Rheumatoid Arthritis Scoring via Anatomy-aware Multiple Instance Learning
arxiv.org·1d
📊AI Performance Profiling
On the Limits of Selective AI Prediction: A Case Study in Clinical Decision Making
arxiv.org·4h
📊AI Performance Profiling
EmoAugNet: A Signal-Augmented Hybrid CNN-LSTM Framework for Speech Emotion Recognition
arxiv.org·1d
🧠Large Language Models (LLMs)
EICAP: Deep Dive in Assessment and Enhancement of Large Language Models in Emotional Intelligence through Multi-Turn Conversations
arxiv.org·1d
🧠Large Language Models (LLMs)
Large Language Models for Oral History Understanding with Text Classification and Sentiment Analysis
arxiv.org·4h
🧠Large Language Models (LLMs)
InterChart: Benchmarking Visual Reasoning Across Decomposed and Distributed Chart Information
arxiv.org·4h
📊AI Performance Profiling
Domain-Specific Fine-Tuning and Prompt-Based Learning: A Comparative Study for developing Natural Language-Based BIM Information Retrieval Systems
arxiv.org·1d
🧠Large Language Models (LLMs)
Ethics2vec: aligning automatic agents and human preferences
arxiv.org·4h
📊AI Performance Profiling
BharatBBQ: A Multilingual Bias Benchmark for Question Answering in the Indian Context
arxiv.org·4h
🧠Large Language Models (LLMs)
Smoothing Slot Attention Iterations and Recurrences
arxiv.org·4d
🧠Large Language Models (LLMs)
Narrative Memory in Machines: Multi-Agent Arc Extraction in Serialized TV
arxiv.org·4h
🔍Retrieval-augmented generation