Language Models
40 tracked items
EPFL News·9d ago
An AI capable of doubt can optimize scientific discovery
arXiv·9d ago
The Emergent Symbolic Structure of Artificial Neural Networks
arXiv·9d ago
Retrieval, Scoring, and Decoding Shape Performance and Stability in LLM-based Conversational Recommendation
arXiv·9d ago
Faster Than Flash: Exploiting Attention Sparsity for Efficient Long-Context Decoding
arXiv·9d ago
A Cognitive Architecture for Shared Autonomy in AUV Operations
arXiv·9d ago
LLM-Driven Autonomous Vehicles Inherit Human Driver Biases in Pedestrian Yielding: Results and Implications From A New Benchmark
arXiv·9d ago
Beyond Language Priors: Diagnosing and Fixing Visual-Origin Hallucinations in Multimodal LLM
arXiv·9d ago
Incremental Risk Assessment of Progressive Elder Financial Scams via Instruction-Tuned Small Language Models
arXiv·9d ago
Distributed Implicit Harm: A Compositional Safety Blind Spot in MLLM-Based Video Moderation
arXiv·9d ago
ViTAL-X: Video-Text Alignment with Cross-Modal Temporal Edits
arXiv·9d ago
A Glance Is All You Need: Single-Pass Fine-Grained Image Captioning with SimLoss
arXiv·9d ago
Assessing Suicide Risk in Arabic Crisis Helpline Calls: A Comparison of Arabic and English Large Language Models
arXiv·9d ago
Beyond Blind Compliance: Benchmarking Task Verification in OCR Reasoning
arXiv·9d ago
Less Is More: Balancing Positive and Negative Space in Visual Concept Blending
arXiv·9d ago
Authority Bias in Conversational Search Engines for Academic Paper Recommendation
arXiv·9d ago
Behaviorally Grounded User Profiles from the Wild for Personalized Alignment and Multi-Perspective Reasoning
arXiv·9d ago
The Potential of Haptic Foundation Models
arXiv·9d ago
Attention Sensitivity Is Not Enough: Dissociating Attention-Level and Behavioural In-Context Learning under Fine-Tuning
arXiv·9d ago
Good Memory Has ECC: Evaluating the Memory of Vision-Language Models Beyond Accuracy
arXiv·9d ago
REAL-Q: E2E LLM Quantization via Dynamic Gradient Descent
arXiv·9d ago
From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling
arXiv·9d ago
RePro: Proof-Verified Benchmark Rewriting for Reliable Evaluation of LLM Mathematical Problem Solving
arXiv·9d ago
CUDA-Harness: Harnessing Agentic CUDA Kernel Generation and Optimization from Natural Language
arXiv·9d ago
Do Multimodal LLMs See Before They Read? Diagnosing Contextual Sycophancy
arXiv·9d ago
Medical Causal Hypothesis Verification with Large Language Models
arXiv·9d ago
Generative artificial intelligence for reliable mechanistic reasoning for corrosion
arXiv·9d ago
QTEA: Ternary LLMs with Sparse Residual Salient Weight and By-Column Optimization
arXiv·9d ago
Do LLMs Know Your Neighborhood? Auditing LLM Priors for Neighborhood-Level Mobility Prediction and Structural Alignment
arXiv·9d ago
Uncovering and Mitigating Aggregation-Induced Reward Hacking in Multi-Reward Reinforcement Learning
arXiv·9d ago
Lingua Franca or Probing Artifact? Rethinking Latent Language in Multilingual LLMs
arXiv·9d ago
LLM-as-a-Demographic: Whom Sociodemographic Prompting Helps, and Whom It Hurts
arXiv·9d ago
Synthetic Worlds for Temporal Evaluation and Knowledge Updating in LLMs
arXiv·9d ago
AdaVLA: Adaptive Step Flow Matching for Training-free Acceleration of Vision-Language-Action Models
arXiv·9d ago
Asymmetries in Spontaneous and Instructed Deception
arXiv·9d ago
OpenAgentFlow: Enabling System-Wide Safety Boundaries for Heterogeneous AI Agent Fleets
arXiv·9d ago
MiNER: Fine-Tuned Biomedical Natural Language Processing for Malaria Disease Entity Recognition in Clinical Texts
medRxiv·9d ago
Benchmarking ten frontier large language models on 1,477 board style multiple choice questions in hematology
medRxiv·9d ago
Are Frontier Large Language Models Safer Than Government-Backed Symptom Checkers for Clinical Self-Triage? A Standardised Vignette Evaluation
VentureBeat·9d ago
Frontier models can recover up to 65% of facts they can't directly recall — just by thinking longer
VentureBeat·9d ago
Anthropic's Claude Fable 5.1 and Mythos 5.1 arrive with a 75% cost reduction for Fable cache reads