Every story we have kept, newest first.
Looking for the daily editions? → Past editions
Page 1366 of 1372
Dual-stream unsupervised model fuses anomaly detection with physics proxies for embedded vehicle monitoring. Distinguishes transient shocks from sustained high-load states like hill climbing.
ArXiv AI · 215d ago
Presents Physics-Enhanced Swin Transformer (PEST) for 3D turbulence. Uses windowed attention, frequency loss, and physics constraints.
ArXiv AI · 215d ago
PELLI is an iterative framework for integrating LLMs into software generation, evaluating code on maintainability, performance, and reliability. It tests five popular LLMs across three domains using Python standards.
ArXiv AI · 215d ago
Calliope creates synchronized narrated EPUB3 e-books from text using open-source TTS like XTTS-v2. Ensures exact audio-text sync via direct timestamps, preserves original layout offline.
ArXiv AI · 215d ago
OmniVL-Guard unifies vision-language forgery detection and grounding with balanced RL. Self-Evolving CoT and ARSPO tackle difficulty bias.
ArXiv AI · 215d ago
OmniSapiens-7B 2.0 uses HARPO RL to train a unified model across heterogeneous social tasks. HARPO balances learning via modulated advantages.
ArXiv AI · 215d ago
NSAM learns symbolic models and action masks automatically during DRL to avoid infeasible actions. It integrates symbolic reasoning with deep policy optimization mutually.
ArXiv AI · 215d ago
White paper integrates nonuniform ellipticity breakthrough with topos-theoretic LRMs. Formalizes sharp Schauder estimates using ghost equations.
ArXiv AI · 215d ago
Neural Additive Experts use mixture-of-experts per feature with context-gated integration for flexible additivity. Targeted regularization ensures smooth transitions from additive to interactive models.
ArXiv AI · 215d ago
SecureScan uses logistic regression, heuristics, and VirusTotal for URL/file/binary triage. Achieves 93.1% accuracy with balanced precision/recall.
ArXiv AI · 215d ago
MalMoE detects encrypted malicious traffic using graph-based Mixture-of-Experts to handle graph drift. It selects optimal 1-hop-GNN experts via a redesigned gate model.
ArXiv AI · 215d ago
Survey organizes MLLM evolution for chart understanding via multimodal fusion. Introduces taxonomy of tasks and datasets.
ArXiv AI · 215d ago
MIPLIB-NL creates natural-language optimization benchmarks from real MIPLIB 2017 instances via structure-aware reverse engineering. Includes 223 validated reconstructions tying NL specs to solver code.
ArXiv AI · 215d ago
MetaphorStar uses end-to-end visual RL for image metaphor understanding, featuring TFQ-Data dataset, TFQ-GRPO method, and TFQ-Bench. MetaphorStar-32B sets SOTA on implication benchmarks, outperforming 20+ MLLMs including Gemini-3.0-pro.
ArXiv AI · 215d ago
AgoraBench tests LLMs in nine bargaining scenarios like deception; utility metrics measure human alignment. MERIT feedback via prompting/finetuning elicits deeper strategy and opponent awareness.
ArXiv AI · 215d ago
Meta-Experience Learning (MEL) enhances RLVR by internalizing error-derived meta-experience into LLM memory. Uses self-verification for contrastive analysis of trajectories.
ArXiv AI · 215d ago
MeCSAFNet uses dual ConvNeXt encoders for visible and non-visible channels in multispectral land cover segmentation. It employs smooth attentional feature fusion with CBAM and ASAU activation.
ArXiv AI · 215d ago
Study compares reasoning vs non-reasoning LLMs on ToM benchmarks, finding no consistent gains and sometimes worse performance. Insights reveal slow thinking collapse, need for adaptive reasoning, and option-matching shortcuts.
ArXiv AI · 215d ago
LOREN introduces low-rank adapters to enable code-rate adaptation in neural receivers without storing separate weights. It freezes a shared base network and trains lightweight adapters per code rate.
ArXiv AI · 215d ago
Evaluates LoRA for parameter-efficient fine-tuning of LLMs on organic reaction datasets like USPTO and C-H functionalisation. Matches full fine-tuning accuracy while preserving multi-task performance and mitigating forgetting.
ArXiv AI · 215d ago
Locomo-Plus benchmarks cognitive memory in LLM agents under cue-trigger disconnects, focusing on latent conversational constraints. It proposes constraint consistency evaluation over string-matching.
ArXiv AI · 215d ago
Study evaluates 17 LLMs on ODD-to-Python code generation for predator-prey model. Assesses executability, fidelity, efficiency via NetLogo baseline.
ArXiv AI · 215d ago
Fine-tuned LLMs like Llama predict mRS scores from admission notes alone. Achieves 33.9% exact 90-day accuracy and 76.3% binary, matching structured baselines.
ArXiv AI · 215d ago
Uses AlphaEvolve to discover interpretable models of human and LLM strategic behavior from data. Analysis on iterated rock-paper-scissors shows frontier LLMs capable of deeper strategy than humans.
ArXiv AI · 215d ago
Prompts pretrained LLMs to create QNP abstractions for generalized planning from domains and tasks. Automated debugging detects/fixes errors iteratively.
ArXiv AI · 215d ago
LLMs generate culturally unrepresentative recipe adaptations unlike humans. Outputs ignore cultural distance correlations from GlobalFusion dataset.
ArXiv AI · 215d ago
Experience report on using LLMs for systematic mapping studies. Highlights time savings in screening and extraction but notes challenges like hallucinations and prompt engineering.
ArXiv AI · 215d ago
DBPlanBench exposes physical query plans for LLM-proposed localized edits, refined via evolutionary search. LLMs leverage semantic knowledge for optimizations like join orderings.
ArXiv AI · 215d ago
A self-evolving system uses Google's Gemini LLMs to autonomously generate, train, and deploy recommendation model improvements. It features an Offline Agent for hypothesis generation and an Online Agent for production validation.
ArXiv AI · 215d ago
LITT introduces a Timing-Transformer architecture that aligns sequential events on a virtual relative timeline for event-timing-focused attention. It enables personalized clinical trajectory interpretations.
ArXiv AI · 215d ago