AI News

⚡ 13 minutes ago
1
1
Zero-Shot Learning in Industrial Scenarios: New Large-Scale Benchmark, Challenges and Baseline (arxiv.org)
2
1
PAFO: Pareto Fairness Optimization for Personalized Reward Modeling (arxiv.org)
3
1
VATS: Exploiting Implicit Authority in Error-Path Injection via Systematic Mutation (arxiv.org)
4
1
Efficient Skill Grounding via Code Refactoring with Small Language Models (arxiv.org)
5
1
UniQL: Towards Dialect-Universal Benchmarking for Text-to-SQL (arxiv.org)
6
1
Knowledge-Inclusive Adaptive Physics-Informed Neural Network for Microbial Interaction Modelling (arxiv.org)
7
1
HARP: Efficient Data Selection for Finetuning Large Language Models (arxiv.org)
8
1
BCG-FM: A Foundation Model for Ambient Cardiac Health Sensing (arxiv.org)
9
1
DSFNet: Learning Dual-Domain Spectral Operators for Multi-Modality Spatio-Temporal Forecasting in Urban Transportation Systems (arxiv.org)
10
1
Cross-LLM Consistency in Inference: Evidence from Shared Interactions (arxiv.org)
11
1
OSMGraphCLIP: Learning Global Location Representations from OpenStreetMap Graphs (arxiv.org)
12
1
SKILL.nb: Selective Formalization and Gated Execution for Durable Agent Workflows (arxiv.org)
13
1
How Small Can You Go? LoRA Fine-Tuning 270M-8B Models for Merchant Information Extraction in Financial Transactions (arxiv.org)
14
1
A Multi-modal Agentic Co-pilot for Evidence Grounded Computational Pathology (arxiv.org)
15
1
When Does Delegation Beat Majority? A Delegation-Based Aggregator for Multi-Sample LLM Inference (arxiv.org)
16
1
PACE: Anytime-Valid Acceptance Tests for Self-Evolving Agents (arxiv.org)
17
1
Think Before You Act: Intention-Guided Reasoning for LLM-Based Location Prediction (arxiv.org)
18
1
Adversarial Robustness of Activation Steering in Large Language Models (arxiv.org)
19
1
Pharmacogenomic Knowledge Graph Augmentation for Graph Neural Network-Based Drug-Drug Interaction Prediction (arxiv.org)
20
1
EssentialGIN: a new approach for gene essentiality prediction based on graph isomorphism neural networks (arxiv.org)
21
1
EvoCSFL: Surrogate-Assisted Evolutionary Client Selection for Efficient and Robust Federated Learning (arxiv.org)
22
1
How Much Dense Attention is Necessary? Oracle-Guided Sparse Prefill for Full/GQA Layers in Hybrid Long-Context Models (arxiv.org)
23
1
FunctionEvolve: Structure-Guided Symbolic Regression with LLMs (arxiv.org)
24
1
Robust In-Context Reinforcement Learning Under Reward Poisoning Attacks (arxiv.org)
25
1
SAGE: An LLM-driven Self Reflective Agentic Framework for Fraud Detection (arxiv.org)
26
1
Curation of a Cardiology Interface Terminology for Highlighting Electronic Health Records using Machine Learning (arxiv.org)
27
1
Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents (arxiv.org)
28
1
Online Agent-as-a-Judge: Situation-Generating Evaluation for Interactive Agents (arxiv.org)
29
1
Ablation-Reversible Heads Don't Transfer: A Stress Test for Mechanistic Role Claims in Transformers (arxiv.org)
30
1
SAW: Stage-Aware Dynamic Weighting for Multi-Objective Reinforcement Learning in Large Language Models (arxiv.org)
31
1
Decoding Naturalistic Emotion Dynamics from the Brain: An LLM-Enhanced Regression Framework (arxiv.org)
32
1
WhiFlash: Accelerating Speculative Decoding with Token-Level Cross-Paradigm Routing (arxiv.org)
33
1
Rosetta Memory: Adaptive Memory for Cross-LLM Agents (arxiv.org)
34
1
Attention at the Theoretical Minimum: A Mathematics of Arrays Framework for Memory-Optimal Transformer Kernels (arxiv.org)
35
1
A Geometry-Aware Triplane Field Network for Vehicle Aerodynamic Prediction (arxiv.org)
36
1
SciTrace: Trajectory-Aware Safety Reasoning for Scientific Discovery Agents (arxiv.org)
37
1
When No Answer Is Correct: Diagnosing Absent Answer Detection for MLLMs in Video Understanding (arxiv.org)
38
1
From Validator Selection to Portfolio Collection Optimization in Proof-of-Stake Blockchains (arxiv.org)
39
1
Beyond Agent Architecture: Execution Assumptions and Reproducibility in LLM-Based Trading Systems (arxiv.org)
40
1
Revisiting the shutdown problem (arxiv.org)
41
1
To Nuke or Not to Nuke: LLMs' (Missing) Ethical Reasoning and Actions in a High-Stakes Decision-Making Simulation (arxiv.org)
42
1
Neuro-Symbolic Injection of LTLf Constraints in Autoregressive Reinforcement Learning Policies (arxiv.org)
43
1
Integrating Deep Learning Demand Forecasting with Multi-Objective Optimization for Circular Coffee Supply Chains: A Data-Driven Framework for Cost, Emissions, and Freshness Management (arxiv.org)
44
1
Benchmarking Open-Ended Multi-Agent Coordination in Language Agents (arxiv.org)
45
1
GenTSE: Enhancing Target Speaker Extraction via a Coarse-to-Fine Generative Language Model (arxiv.org)
46
1
Characterizing the Discrete Geometry of ReLU Networks (arxiv.org)
47
1
scCBGM: Interpretable Single-Cell Counterfactual Editing (arxiv.org)
48
1
Contrast encodes inductive bias: separating slow noise from dynamics in predictive representation learning (arxiv.org)
49
1
Byzantine Cheap Talk: Adversarial Resilience and Topology Effects in LLM Coordination Games (arxiv.org)
50
1
On the Wasserstein Geodesic Principal Component Analysis of probability measures (arxiv.org)