All Updates
Page 1389 of 1398
February 12, 2026
PiT-PO Boosts Equation Discovery with RL
PiT-PO uses reinforcement learning to evolve LLMs for symbolic regression, enforcing physical validity and parsimony. It treats LLMs as adaptive generators updated by search feedback. Achieves SOTA on benchmarks and discovers novel turbulence models.
Physics-Augmented Vehicle Health Monitoring
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. Runs efficiently on RISC-V ECUs.
PEST Masters 3D Turbulence Simulation
Presents Physics-Enhanced Swin Transformer (PEST) for 3D turbulence. Uses windowed attention, frequency loss, and physics constraints. Outperforms baselines in accuracy and stability.
PELLI Framework Boosts LLM Code Quality
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. GPT-4T and Gemini outperform others, with prompt design impacting quality.
Open-Source TTS E-book Narrator
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. Avoids cloud privacy and cost issues.
OmniVL-Guard Fights Multimodal Forgeries
OmniVL-Guard unifies vision-language forgery detection and grounding with balanced RL. Self-Evolving CoT and ARSPO tackle difficulty bias. Excels in zero-shot generalization.
OmniSapiens: HARPO for Social Behaviors
OmniSapiens-7B 2.0 uses HARPO RL to train a unified model across heterogeneous social tasks. HARPO balances learning via modulated advantages. It outperforms baselines by up to 16.85% with robust reasoning.
NSAM: Neuro-Symbolic Action Masking in DRL
NSAM learns symbolic models and action masks automatically during DRL to avoid infeasible actions. It integrates symbolic reasoning with deep policy optimization mutually. Evaluations show improved sample efficiency and fewer violations.
Neurosymbolic AI Conquers Schauder Theory
White paper integrates nonuniform ellipticity breakthrough with topos-theoretic LRMs. Formalizes sharp Schauder estimates using ghost equations. Enables autonomous proofs in calculus of variations.
NAEs Balance Interpretability and Accuracy
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. Outperforms on accuracy while preserving feature explanations.
Multi-Layer AI Malware Detector
SecureScan uses logistic regression, heuristics, and VirusTotal for URL/file/binary triage. Achieves 93.1% accuracy with balanced precision/recall. Employs gray-zone logic to cut false positives.
MoE for Drift-Aware Malicious Traffic Detection
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. Trained with two-stage strategy and augmentation for real-time precision.
MLLMs Survey on Chart Fusion
Survey organizes MLLM evolution for chart understanding via multimodal fusion. Introduces taxonomy of tasks and datasets. Highlights limitations in perception and reasoning, suggesting alignment and RL enhancements.
MIPLIB-NL for Industrial Optimization Benchmarks
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. Reveals LLM failures on large-scale problems.
MetaphorStar Masters Image Metaphor Reasoning
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. Improves general visual reasoning via scaling analyses.
MERIT Boosts LLM Negotiation Skills
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. Outperforms baselines in negotiation power and acquisition.
MEL Boosts LLM Reasoning via Meta-Experience
Meta-Experience Learning (MEL) enhances RLVR by internalizing error-derived meta-experience into LLM memory. Uses self-verification for contrastive analysis of trajectories. Achieves 3.92%-4.73% Pass@1 gains across model sizes.
MeCSAFNet Boosts Multispectral Segmentation
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. Outperforms baselines like U-Net and SegFormer by up to 19% mIoU on FBP and Potsdam datasets.
LRMs Fail to Transfer Reasoning to ToM
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. Interventions like S2F and T2M mitigate issues.
LOREN: Low-Rank Adaptation for Neural Receivers
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. Achieves comparable performance with major hardware savings.