AI News

⚡ 6 minutes ago
1
1
Representational Capacity: Geometric Limits on Feature Representation in Transformer Language Models (arxiv.org)
2
1
Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models (arxiv.org)
3
1
KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks (arxiv.org)
4
1
Optimal and exact recovery on the general nonuniform Hypergraph Stochastic Block Model (arxiv.org)
5
1
Conformal Language Modeling via Posterior Sampling (arxiv.org)
6
1
WISE-HAR: A Generalizable Ensemble Deep Learning Framework for WiFi-Based Human Activity Recognition (arxiv.org)
7
1
A Sparse Bayesian Learning Algorithm for Estimation of Interaction Kernels in Motsch-Tadmor Model (arxiv.org)
8
1
Inducing Reasoning Primitives from Agent Traces (arxiv.org)
9
1
Efficient ASR Training with Conversations that Never Happened (arxiv.org)
10
1
Learning Coherent Representations: A Topological Approach to Interpretability (arxiv.org)
11
1
CoMPAS3D: A Dataset and Benchmark for Interactive Motion (arxiv.org)
12
1
RRISE: Robust Radius Inference via a Surrogate Estimator (arxiv.org)
13
1
NetKV: Network-Aware Decode Instance Selection for Disaggregated LLM Inference (arxiv.org)
14
1
DELTAMEM: Incremental Experience Memory for LLM Agents via Residual Trees (arxiv.org)
15
1
dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching (arxiv.org)
16
1
Neural Posterior Estimation for Stochastic Epidemic Models Using Final Outcome Data (arxiv.org)
17
1
ToolGate: Token-Efficient Pre-Call Control for Tool-Augmented Vision-Language Agents (arxiv.org)
18
1
The Impact of Configuring Agentic AI Coding Tools on Build-vs-Buy Decisions: A Study Protocol (arxiv.org)
19
1
High-Dimensional Latents Should Be Diagnosed Through Phase Structure (arxiv.org)
20
1
scTranslation: A Comprehensive Benchmark for Single-Cell Multi-Omics Modality Translation (arxiv.org)
21
1
Hedge-Bench: Benchmarking Agents on Hard, Realistic Tasks Pertaining to Financial Reasoning (arxiv.org)
22
1
Local and Global Contraction Principles for MCMC Mixing (arxiv.org)
23
1
Agent libOS: A Library-OS-Inspired Runtime for Long-Running, Capability-Controlled LLM Agents (arxiv.org)
24
1
TRAP: Hijacking VLA CoT-Reasoning via Adversarial Patches (arxiv.org)
25
1
ERP-XTTN: Interpretable Prototype-Guided Cross-Attention for Cross-Subject ERP Classification (arxiv.org)
26
1
Fast Unlearning at Scale via Margin Self-Correction (arxiv.org)
27
1
Hierarchical RBF-KAN and RBF-SKAN Architectures for Multidimensional Function Approximation and Random Field Learning (arxiv.org)
28
1
The Reliability Gap in Benchmark Auditing: Distribution Shift and Scale as Failure Modes of Contamination Detection (arxiv.org)
29
1
Gate AI: LLM Security Benchmark Evaluation Methodology and Results (arxiv.org)
30
1
Multi$^2$: Hierarchical Multi-Agent Decision-Making with LLM-Based Agents in Interactive Environments (arxiv.org)
31
1
The Violation Situation Pattern: A Knowledge-Graph Pattern for Compliance Violations (arxiv.org)
32
1
CP-Agent: Context-Aware Multimodal Reasoning for Cellular Morphological Profiling under Chemical Perturbations (arxiv.org)
33
1
Position: Adversarial ML for LLMs Is Not Making Any Progress (arxiv.org)
34
1
SEAOTTER: Sensor Embedded Autoencoding with One-Time Transcode for Efficient Reconstruction (arxiv.org)
35
1
CoralBay: A Self-Supervised CT Foundation Model (arxiv.org)
36
1
PyraMathBench: Evaluating and Improving Mathematical Capability in Large Language Models (arxiv.org)
37
1
Improvise, Adapt, Overcome: An On-The-Fly Multifidelity Algorithm for Efficient Machine Learning (arxiv.org)
38
1
Building Trust in Black-box Optimization: A Comprehensive Framework for Explainability (arxiv.org)
39
1
Spectral Asymptotics of Neural Network Loss Landscapes: An Exact Decomposition of the Curvature Exponent (arxiv.org)
40
1
R2DN: Scalable Parameterization of Contracting and Lipschitz Recurrent Deep Networks (arxiv.org)
41
1
Reasoning Structure of Large Language Models (arxiv.org)
42
1
MOSAIC: Efficient Mixture-of-Agent Scheduling via Adaptive Aggregation and Inference Concurrency (arxiv.org)
43
1
Large Byte Model: Teaching Language Models About Compiled Code (arxiv.org)
44
1
AUGUSTE: Online-Learning dApp for Predictive URLLC Scheduling (arxiv.org)
45
1
Anomalies in Multivariate Time Series Benchmarks Are Mostly Univariate (arxiv.org)
46
1
A formal definition and meta-model for a machine theory of mind (arxiv.org)
47
1
Cross-Lingual Token Arbitrage: Optimizing Code Agent Context Windows via Local LLM Preprocessing (arxiv.org)
48
1
What Do Students Learn? A Feature-Level Analysis of Dark Knowledge (arxiv.org)
49
1
Learning to Solve, Forgetting to Retain: Correct-Set Turnover in RLVR (arxiv.org)
50
1
AnchorMoE: Interpretable Time Series Classification via Anchor-Routed MoE (arxiv.org)