AI News

⚡ 5 minutes ago
1
1
Evolving Demonstration Optimization for Chain-of-Thought Feature Transformation (arxiv.org)
2
1
Causally Grounded Mechanistic Interpretability for LLMs with Faithful Natural-Language Explanations (arxiv.org)
3
1
PoultryLeX-Net: Domain-Adaptive Dual-Stream Transformer Architecture for Large-Scale Poultry Stakeholder Modeling (arxiv.org)
4
1
Equivariant Asynchronous Diffusion: An Adaptive Denoising Schedule for Accelerated Molecular Conformation Generation (arxiv.org)
5
1
SiMPO: Measure Matching for Online Diffusion Reinforcement Learning (arxiv.org)
6
1
Tackling Length Inflation Without Trade-offs: Group Relative Reward Rescaling for Reinforcement Learning (arxiv.org)
7
1
ADVERSA: Measuring Multi-Turn Guardrail Degradation and Judge Reliability in Large Language Models (arxiv.org)
8
1
Revisiting Sharpness-Aware Minimization: A More Faithful and Effective Implementation (arxiv.org)
9
1
A Survey of Weight Space Learning: Understanding, Representation, and Generation (arxiv.org)
10
1
Optimal Expert-Attention Allocation in Mixture-of-Experts: A Scalable Law for Dynamic Model Design (arxiv.org)
11
1
Cross-embodied Co-design for Dexterous Hands (arxiv.org)
12
1
Variance-Aware Adaptive Weighting for Diffusion Model Training (arxiv.org)
13
1
REI-Bench: Can Embodied Agents Understand Vague Human Instructions in Task Planning? (arxiv.org)
14
1
Improving TabPFN's Synthetic Data Generation by Integrating Causal Structure (arxiv.org)
15
1
Flexible Cutoff Learning: Optimizing Machine Learning Potentials After Training (arxiv.org)
16
1
Silhouette-Driven Instance-Weighted $k$-means (arxiv.org)
17
1
Reinforcement Learning with Conditional Expectation Reward (arxiv.org)
18
1
Efficient Bayesian Updates for Deep Active Learning via Laplace Approximations (arxiv.org)
19
1
Why LLMs Fail: A Failure Analysis and Partial Success Measurement for Automated Security Patch Generation (arxiv.org)
20
1
A New Tensor Network: Tubal Tensor Train and Its Applications (arxiv.org)
21
1
A Novel Single-Layer Quantum Neural Network for Approximate SRBB-Based Unitary Synthesis (arxiv.org)
22
1
Training with Pseudo-Code for Instruction Following (arxiv.org)
23
1
MCMC Informed Neural Emulators for Uncertainty Quantification in Dynamical Systems (arxiv.org)
24
1
DT-BEHRT: Disease Trajectory-aware Transformer for Interpretable Patient Representation Learning (arxiv.org)
25
1
Rethinking the Harmonic Loss via Non-Euclidean Distance Layers (arxiv.org)
26
1
Ranking Reasoning LLMs under Test-Time Scaling (arxiv.org)
27
1
Beam-Plasma Collective Oscillations in Intense Charged-Particle Beams: Dielectric Response Theory, Langmuir Wave Dispersion, and Unsupervised Detection via Prometheus (arxiv.org)
28
1
LiTo: Surface Light Field Tokenization (arxiv.org)
29
1
Muscle Synergy Priors Enhance Biomechanical Fidelity in Predictive Musculoskeletal Locomotion Simulation (arxiv.org)
30
1
HTMuon: Improving Muon via Heavy-Tailed Spectral Correction (arxiv.org)
31
1
VERI-DPO: Evidence-Aware Alignment for Clinical Summarization via Claim Verification and Direct Preference Optimization (arxiv.org)
32
1
Multilingual AI-Driven Password Strength Estimation with Similarity-Based Detection (arxiv.org)
33
1
GroundCount: Grounding Vision-Language Models with Object Detection for Mitigating Counting Hallucinations (arxiv.org)
34
1
Targeted Bit-Flip Attacks on LLM-Based Agents (arxiv.org)
35
1
CUAAudit: Meta-Evaluation of Vision-Language Models as Auditors of Autonomous Computer-Use Agents (arxiv.org)
36
1
Training Language Models via Neural Cellular Automata (arxiv.org)
37
1
UAV traffic scene understanding: A cross-spectral guided approach and a unified benchmark (arxiv.org)
38
1
Amnesia: Adversarial Semantic Layer Specific Activation Steering in Large Language Models (arxiv.org)
39
1
Resource-constrained Amazons chess decision framework integrating large language models and graph attention (arxiv.org)
40
1
Breaking the Stochasticity Barrier: An Adaptive Variance-Reduced Method for Variational Inequalities (arxiv.org)
41
1
G-STAR: End-to-End Global Speaker-Tracking Attributed Recognition (arxiv.org)
42
1
Evaluating Progress in Graph Foundation Models: A Comprehensive Benchmark and New Insights (arxiv.org)
43
1
Artificial Intelligence as a Catalyst for Innovation in Software Engineering (arxiv.org)
44
1
Does AI See like Art Historians? Interpreting How Vision Language Models Recognize Artistic Style (arxiv.org)
45
1
Architecture-Aware LLM Inference Optimization on AMD Instinct GPUs: A Comprehensive Benchmark and Deployment Study (arxiv.org)
46
1
Actor-Accelerated Policy Dual Averaging for Reinforcement Learning in Continuous Action Spaces (arxiv.org)
47
1
Why Does It Look There? Structured Explanations for Image Classification (arxiv.org)
48
1
Class Incremental Learning with Task-Specific Batch Normalization and Out-of-Distribution Detection (arxiv.org)
49
1
Aligning Large Language Models with Searcher Preferences (arxiv.org)
50
1
A Retrieval-Augmented Language Assistant for Unmanned Aircraft Safety Assessment and Regulatory Compliance (arxiv.org)