AI News

⚡ 14 minutes ago
1
1
On the Collapse of Generative Paths: A Criterion and Correction for Diffusion Steering (arxiv.org)
2
1
Boosting RL-Based Visual Reasoning with Selective Adversarial Entropy Intervention (arxiv.org)
3
1
PolarMem: A Training-Free Polarized Latent Graph Memory for Verifiable Vision-Language Models (arxiv.org)
4
1
Structure Enables Effective Self-Localization of Errors in LLMs (arxiv.org)
5
1
Breaking the Reversal Curse in Autoregressive Language Models via Identity Bridge (arxiv.org)
6
1
Beyond End-to-End Video Models: An LLM-Based Multi-Agent System for Educational Video Generation (arxiv.org)
7
1
Prototype Transformer: Towards Language Model Architectures Interpretable by Design (arxiv.org)
8
1
REAL: Resolving Knowledge Conflicts in Knowledge-Intensive Visual Question Answering via Reasoning-Pivot Alignment (arxiv.org)
9
1
When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation (arxiv.org)
10
1
Retrieval-aligned Tabular Foundation Models Enable Robust Clinical Risk Prediction in Electronic Health Records Under Real-world Constraints (arxiv.org)
11
1
Perspective on Bias in Biomedical AI: Preventing Downstream Healthcare Disparities (arxiv.org)
12
1
RadAgent: A tool-using AI agent for stepwise interpretation of chest computed tomography (arxiv.org)
13
1
ANDRE: An Attention-based Neuro-symbolic Differentiable Rule Extractor for Inductive Logic Programming (arxiv.org)
14
1
UrbanFusion: Stochastic Multimodal Fusion for Contrastive Learning of Robust Spatial Representations (arxiv.org)
15
1
Tractable Shapley Values and Interactions via Tensor Networks (arxiv.org)
16
1
Symbolic Neural Generation with Applications to Lead Discovery in Drug Design (arxiv.org)
17
1
DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing (arxiv.org)
18
1
Scaling depth capacity via zero/one-layer model expansion (arxiv.org)
19
1
FIRM: Federated In-client Regularized Multi-objective Alignment for Large Language Models (arxiv.org)
20
1
WUSH: Near-Optimal Adaptive Transforms for LLM Quantization (arxiv.org)
21
1
Position: Current Benchmarking Hinders Real Progress in Deep Learning for Time Series Forecasting (arxiv.org)
22
1
Early Prediction of Liver Cirrhosis Up to Two Years in Advance: A Machine Learning Study Benchmarking Against the FIB-4 and APRI Scores (arxiv.org)
23
1
When Does Predictive Inverse Dynamics Outperform Behavior Cloning? (arxiv.org)
24
1
Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation (arxiv.org)
25
1
From Zero to Hero: Advancing Zero-Shot Foundation Models for Tabular Outlier Detection (arxiv.org)
26
1
Robust Learning of a Group DRO Neuron (arxiv.org)
27
1
Multi-Objective Reinforcement Learning for Tactical Decision Making for Trucks in Highway Traffic (arxiv.org)
28
1
Consistency Deep Equilibrium Models (arxiv.org)
29
1
SurrogateSHAP: Training-Free Contributor Attribution for Text-to-Image (T2I) Models (arxiv.org)
30
1
Knowledge-Informed Kernel State Reconstruction from Heterogeneous Partial Observations (arxiv.org)
31
1
GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via Unlearning (arxiv.org)
32
1
Adaptive Exploration for Latent-State Bandits (arxiv.org)
33
1
Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation (arxiv.org)
34
1
LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents (arxiv.org)
35
1
Zero-Shot Off-Policy Learning (arxiv.org)
36
1
Probabilistic Performance Guarantees for Multi-Task Reinforcement Learning (arxiv.org)
37
1
Interpretability in Deep Time Series Models Demands Semantic Alignment (arxiv.org)
38
1
naPINN: Noise-Adaptive Physics-Informed Neural Networks for Recovering Physics from Corrupted Measurement (arxiv.org)
39
1
Beware of the Batch Size: Hyperparameter Bias in Evaluating LoRA (arxiv.org)
40
1
The Alignment Curse: Modality Alignment Supercharges Audio Attacks via Text Transfer (arxiv.org)
41
1
Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks (arxiv.org)
42
1
Lookahead Sample Reward Guidance for Test-Time Scaling of Diffusion Models (arxiv.org)
43
1
When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs (arxiv.org)
44
1
Equilibrium Propagation for Non-Conservative Systems (arxiv.org)
45
1
From Evaluation to Design: Using Potential Energy Surface Smoothness Metrics to Guide Machine Learning Interatomic Potential Architectures (arxiv.org)
46
1
Tempora: Characterising the Time-Contingent Utility of Online Test-Time Adaptation (arxiv.org)
47
1
Principle-Evolvable Scientific Discovery via Uncertainty Minimization (arxiv.org)
48
1
Vegas: Self-Speculative Decoding with Verification-Guided Sparse Attention (arxiv.org)
49
1
DeepIPCv2: LiDAR-powered Robust Environmental Perception and Navigational Control for Autonomous Vehicle (arxiv.org)
50
1
Recent Advances in Multi-modal 3D Intelligence: A Comprehensive Survey and Evaluation (arxiv.org)