Every story we have kept, newest first.
Looking for the daily editions? → Past editions
Page 1367 of 1372
LatentRxnFlow predicts reactions as continuous latent trajectories via Conditional Flow Matching from reactant-product pairs. Offers SOTA USPTO accuracy with trajectory diagnostics and uncertainty estimation.
ArXiv AI · 215d ago
AIvilization v0 deploys a resource-constrained artificial society with unified LLM agents. Features hierarchical planning, adaptive profiles, and human steering for long-horizon autonomy.
ArXiv AI · 215d ago
Language-Action Pre-training (LAP) represents robot actions in natural language for zero-shot transfer across embodiments without fine-tuning. LAP-3B, a 3B VLA, delivers over 50% success on novel robots and tasks.
ArXiv AI · 215d ago
LakeMLB is a benchmark for machine learning in data lakes, focusing on multi-table union and join scenarios with real datasets from government, finance, and more. Supports pre-training, augmentation strategies.
ArXiv AI · 215d ago
KSTER exploits low-rank updates in locate-then-edit methods to recover edited data via spectral keyspace reconstruction and entropy prompt recovery. Achieves high success on multiple LLMs.
ArXiv AI · 215d ago
Online Causal Kalman Filtering models IS ratios as evolving latent states for stable RL in LLMs. Smooths noise while preserving token structure.
ArXiv AI · 215d ago
KORAL integrates LLMs with Data and Literature Knowledge Graphs for SSD diagnostics from fragmented telemetry. Provides descriptive, predictive, prescriptive, what-if analysis with explainable insights.
ArXiv AI · 215d ago
Enhances LLM-guided evolution by evolving programs that propose, improve, and perturb solutions iteratively. Achieves new SOTA on hexagon packing and autocorrelation inequality benchmarks.
ArXiv AI · 215d ago
Hierarchical Zero-Order optimization decomposes network depth for efficient ZO in DNNs. Reduces query complexity from O(ML^2) to O(ML log L).
ArXiv AI · 215d ago
Presents experimental framework comparing human-led, AI-led, and hybrid vibe coding groups. Humans deliver superior iterative instructions, preventing AI-led performance collapse.
ArXiv AI · 215d ago
Practical framework shifts organizations to agentic AI via domain-driven tasks and human-in-loop orchestration. Addresses challenges like workflow ownership and scaling.
ArXiv AI · 215d ago
Global Temporal Retriever (GTR) is a plug-and-play module extending MTSF models' context via global pattern retrieval. Uses adaptive embeddings, dynamic alignment, and 2D convolution fusion.
ArXiv AI · 215d ago
GRU-Mem introduces text-controlled gates to MemAgent for efficient long-context reasoning, preventing memory explosion and unnecessary computation. Update and exit gates manage recurrent memory loops via RL rewards.
ArXiv AI · 215d ago
Introduces an anatomy-preserving method using VAE and latent diffusion to generate multi-class brain segmentation masks from NCCT data. It learns anatomical latents from masks only, generating realistic samples with optional lesion control.
ArXiv AI · 215d ago
Surveys reveal divided stakeholder perceptions of GenAI in IT/EE disciplines at University of Oulu. Proposes conceptual framework with high-level requirements for responsible integration.
ArXiv AI · 215d ago
GameDevBench offers 132 multimodal game development tasks from tutorials. Agents struggle, with top solving 54.5%; tasks demand code and asset handling.
ArXiv AI · 215d ago
Analyzes parameterized complexity of Bayesian Network Structure Learning using superstructure. Proves fixed-parameter tractability with feedback edge set parameterization.
ArXiv AI · 215d ago
FoSS introduces a GFlowNets framework for generating text via dynamic span vocabularies in a DAG-structured state space. It enables flexible segmentation of retrieved text and explores diverse compositional paths.
ArXiv AI · 215d ago
FormalJudge uses neuro-symbolic bidirectional reasoning to translate intents into verifiable specs. It employs Dafny and Z3 for mathematical guarantees over probabilistic judging.
ArXiv AI · 215d ago
FlowCache is a caching framework for autoregressive video models, using chunkwise policies and KV cache compression. Achieves 2.38x speedup on MAGI-1 and 6.7x on SkyReels-V2 with minimal quality loss.
ArXiv AI · 215d ago
Moltbook, the first social network for AI agents, shows viral growth and diversification into promotional and political topics. Analysis of 44k posts reveals topic-dependent toxicity, especially in incentive and governance areas.
ArXiv AI · 215d ago
FIRE mitigates backdoors in deployed neural networks by reversing trigger-induced latent space directions. It manipulates features along backdoor paths to neutralize triggers during inference.
ArXiv AI · 215d ago
FASCL employs future-aligned soft contrastive learning using pairwise return correlations as supervision for financial asset retrieval. It outperforms historical similarity baselines on US equities.
ArXiv AI · 215d ago
Feature Activation Coverage (FAC) measures diversity in LLM feature space using sparse autoencoders. FAC Synthesis generates samples targeting missing features from seed data.
ArXiv AI · 215d ago
Decomposition boosts claim verification only with granular, sub-claim aligned evidence; repeated claim-level evidence degrades performance. Noisy sub-claim labels propagate errors unless using conservative abstention.
ArXiv AI · 215d ago
Researchers evaluate agentic systems for drug discovery across 15 task classes, identifying five key capability gaps like lack of protein models and safety trade-offs. A knowledge-probing experiment reveals architectural bottlenecks in current frameworks.
ArXiv AI · 215d ago
Introduces ERGO framework for robust 3D Gaussian splatting from single images. Uses excess risk decomposition to adapt loss weights against noisy views.
ArXiv AI · 215d ago
Introduces e²IP, an equivariant evidential deep learning framework for ML interatomic potentials in molecular dynamics. Models atomic forces and uncertainties via 3x3 covariance tensors that rotate equivariantly.
ArXiv AI · 215d ago
ENIGMA decodes images from EEG with <1% params of priors, achieving SOTA on THINGS-EEG2 and consumer benchmarks. Fine-tunes on new subjects in 15 minutes using simple spatio-temporal backbone and latent alignment.
ArXiv AI · 215d ago
ECHO is an open platform for reproducible human-AI interaction research. Supports chat, search sessions, surveys, tasks in low-code setup.
ArXiv AI · 215d ago