AI News

⚡ 8 minutes ago
1
1
HERO: Hindsight-Enhanced Reflection from Environment Observations for Agentic Self-Distillation (arxiv.org)
2
1
TouchThinker: Scaling Tactile Commonsense Reasoning to the Open World with Large-scale Data and Action-aware Representation (arxiv.org)
3
1
TreeSeeker: Tree-Structured Trial, Error, and Return in Deep Search (arxiv.org)
4
1
Lung-R1: A Knowledge Graph-Guided LLM for Pulmonary Diagnostic Reasoning (arxiv.org)
5
1
Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agents (arxiv.org)
6
1
Mind the Perspective: Let's Reason Recursively for Theory of Mind (arxiv.org)
7
1
When Do Data-Driven Systems Exhibit the Capability to Infer? (arxiv.org)
8
1
SVoT: State-aware Visualization-of-Thought for Spatial Reasoning via Reinforcement Learning (arxiv.org)
9
1
Toward Trustworthy AI: Multi-Target Adversarial Attacks and Robust Defenses for Continuous Data Summarization (arxiv.org)
10
1
Embodied-BenchClaw: An Autonomous Multi-Agent System for Embodied Spatial Intelligence Benchmark Construction (arxiv.org)
11
1
The Art of Interrogation: Consistency Amplifies Factuality in Spatial Reasoning (arxiv.org)
12
1
MODF-SIR: A Multi-agent Omni-modal Distilled Framework for Social Intelligence Reasoning (arxiv.org)
13
1
Human-Enhanced Loop Modeling (HELM): Agent-Based Finite Element Modeling of Concrete Bridge Barriers (arxiv.org)
14
1
Existential Indifference: Self-Nonpreservation as a Necessary Architectural Condition for Aligned Superintelligence (or: The Suicidal AI) (arxiv.org)
15
1
A Lightweight Multi-Agent Framework for Automated Concrete Barrier Design (arxiv.org)
16
1
Automating Geometry-Intensive Compliance Checking in BIM: Graph-Based Semantic Reasoning Framework (arxiv.org)
17
1
IntElicit: Eliciting and Assessing Contextualized Creativity via Dialogue Policy Optimization (arxiv.org)
18
1
Towards Responsibly Non-Compliant Machines (arxiv.org)
19
1
The Impossibility of Eliciting Latent Knowledge (arxiv.org)
20
1
A Five-Plane Reference Architecture for Runtime Governance of Production AI Agents (arxiv.org)
21
1
PROJECTMEM: A Local-First, Event-Sourced Memory and Judgment Layer for AI Coding Agents (arxiv.org)
22
1
Nonslop: A Gamified Experiment in Human-AI Collaborative Writing (arxiv.org)
23
1
From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data (arxiv.org)
24
1
PoQ-Judge: A Multi-Architecture Evaluation Framework for Cost-Aware Proof-of-Quality in Decentralized LLM Inference (arxiv.org)
25
1
MA-DLE: Speech-based Automatic Depression Level Estimation via Memory Augmentation (arxiv.org)
26
1
The Structural Attention Tax: How Retrieval Format Hijacks In-Context Learning Independent of Content (arxiv.org)
27
1
NightFeats @ MMU-RAGent NeurIPS 2025: A Context-Optimized Multi-Agent RAG System for the Text-to-Text Track (arxiv.org)
28
1
Hybrid Iterative Neural Low-Regularity Integrator for Nonlinear Dispersive Equations (arxiv.org)
29
1
RePAIR: Predictive Self-Supervised Representation Learning in Chess (arxiv.org)
30
1
Attention by Synchronization in Coupled Oscillator Networks (arxiv.org)
31
1
MemNovo: Look Back at the Spectrum for Balanced De Novo Peptide Sequencing from Mass Spectrometry (arxiv.org)
32
1
Beyond representational alignment with brain-guided language models for robust reasoning (arxiv.org)
33
1
HAMNO: A Hierarchical Adaptive Multi-scale Neural Operator with Physics-Informed Learning for Dynamical Systems (arxiv.org)
34
1
PAWS: Preference Learning with Advantage-Weighted Segments (arxiv.org)
35
1
Time-Series Foundation Model Embeddings for Remaining Useful Life Estimation (arxiv.org)
36
1
Tabular Foundation Models for Clinical Survival Analysis via Survival-Aware Adaptation (arxiv.org)
37
1
Generalization Hacking: Models Can Game Reinforcement Learning by Preventing Behavioral Generalization (arxiv.org)
38
1
Reliable Error Estimation for PINNs: Lower and Upper A Posteriori Bounds (arxiv.org)
39
1
Simplicity Suffices for Parameter Noise Injection in Stochastic Gradient Descent (arxiv.org)
40
1
Neural-Parameterized Cellular Automata for Wildfire Spread (arxiv.org)
41
1
Efficient Time Series Clustering from Multiscale Reservoir Dynamics with Granular-Ball Anchoring Graph Optimization (arxiv.org)
42
1
A Riemannian Approach to Low-Rank Optimal Transport (arxiv.org)
43
1
Unstable Features, Reproducible Subspaces: Understanding Seed Dependence in Sparse Autoencoders (arxiv.org)
44
1
SpAArSIST: Sparsified AASIST for Efficient and Reliable Anti-Spoofing (arxiv.org)
45
1
Latent World Recovery for Multimodal Learning with Missing Modalities (arxiv.org)
46
1
PCA-Enhanced Adaptive NVAR Framework for High-Resolution Sea Surface Temperature Forecasting in the East Sea (arxiv.org)
47
1
nD-RoPE: A Generalized RoPE for n-Dimensional Position Embedding (arxiv.org)
48
1
How Low Can You Go? Active Learning for Sparse Model Discovery in the Ultra-Low-Data Limit (arxiv.org)
49
1
Implicit Neural Representations of Individual Behavior (arxiv.org)
50
1
Re-evaluating Confidence Remasking in Masked Diffusion Language Models (arxiv.org)