TechniqueRLHF / Alignment8 recent entries12 Aug 2026Sensor-Informed Per-Point Covariance for Structured-Light 3D ImagingarXiv:2608.10888v1 Announce Type: new Abstract: Per-point uncertainty models are important in structured-light 3D reconstruction for probabilistic registration, fusion, and quality assessment. In prac→12 Aug 2026SCOUT: Symmetric Consensus Outlier Detection for Failure Localization in LLM Pre-TrainingarXiv:2608.11034v1 Announce Type: cross Abstract: In LLM pre-training, synchronization propagates rank-local stalls, slowdowns, and numerical errors into job-wide symptoms, obscuring their origin. Exi
TechniqueRAG8 recent entries6 Aug 2026MultiPathFormer: Towards a Foundation Model for Multipath Wireless PropagationarXiv:2608.05076v1 Announce Type: cross Abstract: Recent advances in machine learning have enabled training of wireless foundation models, which aim to support tasks such as channel estimation, beam p→7 Aug 2026UQ-Loc: Uncertainty-Aware LiDAR Scene Coordinate RegressionarXiv:2608.06307v1 Announce Type: new Abstract: LiDAR-based Scene Coordinate Regression (SCR) maps point clouds directly to 3D scene coordinates, enabling precise 6-DoF localisation without explicit m→10 Aug 2026RAG-art: Build Your Own Art Expert with ollamaI built myself a personal AI art history assistant https://github.com/lololerigolo60/RAG-art/tree/main I love art history but I have way too many books, PDFs, and notes scattered everywhere. So I buil→11 Aug 2026Integrated Multimodal AI System for Retrieval-Augmented Reasoning, Object Sensing, and Damage AnalysisarXiv:2608.08935v1 Announce Type: new Abstract: This work presents a unified multimodal AI system for damage assessment that integrates retrieval-augmented generation (RAG) models, thermal spectrum pe→11 Aug 2026AquiLLM: An Architecture for Supporting Tacit Knowledge Capture in Research GroupsarXiv:2608.08883v1 Announce Type: new Abstract: Recent advances in retrieval-augmented generation (RAG) and large language models (LLMs) enable researchers to integrate AI into scientific workflows. H→11 Aug 2026Agentic AI-driven Immersive Simulation: A Knowledge-Aware Virtual Training Platform forHigh Dose Rate (HDR) BrachytherapyarXiv:2608.08163v1 Announce Type: new Abstract: The convergence of the Metaverse and Large Language Model (LLM)-based AI agent is catalyzing a shift toward autonomous, immersive, and personalized peda→12 Aug 2026Retrieval-Corrected Conformal Prediction for Time SeriesarXiv:2608.10553v1 Announce Type: cross Abstract: Conformal prediction (CP) provides distribution-free prediction intervals for fixed forecasters, but its standard calibration procedure is often ineff→12 Aug 2026RAG for regular users?One of the reasons I got into local LLMs was the possibility of getting answers using my own documents and books (a few hundreds) instead of having to search through them manually. However since I'm n
TechniqueAgents8 recent entries12 Aug 2026Toward the Cognitive--Physical Limits of Embodied Intelligence through a World-Model-Centric Autonomous Racing AgentarXiv:2608.10618v1 Announce Type: new Abstract: Embodied artificial intelligence aims to develop agents that perceive, reason, and act through continuous interaction with the physical world. However, →12 Aug 2026Sheaf-Based Federated Representation LearningarXiv:2608.10016v1 Announce Type: cross Abstract: Heterogeneous federated systems require agents to learn and exchange informative representations despite differences in data distributions, sensing mo→12 Aug 2026R4DSG: Relative 4D Scene Graph Memory for Object-Centric Question Answering in Long Egocentric VideoarXiv:2608.11017v1 Announce Type: cross Abstract: Long-horizon egocentric video is a rich substrate for wearable AI assistants, but object-centric questions such as where an item was moved, when it la→12 Aug 2026Quantum Coordination Advantages in AI State-Tracking Tasks: Semantic Compilation and Latent MemoryarXiv:2608.11066v1 Announce Type: cross Abstract: We prove inference-time quantum coordination advantages for specified AI state-tracking tasks. A solver compresses semantic history into a future-acce→12 Aug 2026Easy3D-Labels: Supervising Semantic Occupancy Estimation with 3D Pseudo-Labels for Automotive PerceptionarXiv:2509.26087v5 Announce Type: replace Abstract: In perception for automated vehicles, safety is critical not only for the driver but also for other agents in the scene, particularly vulnerable roa→12 Aug 2026Conversational Orchestration for Organic 6GarXiv:2608.10714v1 Announce Type: cross Abstract: The Organic 6G vision of a network of networks spanning an edge-cloud continuum complemented by non-terrestrial resources requires, to realize its pro→12 Aug 2026Beyond Detection: Evaluating Defensive LLMs Against AI-Generated Social Engineering in Live Turn-by-Turn InteractionarXiv:2608.10239v1 Announce Type: new Abstract: Generative AI makes social-engineering attacks more fluent, adaptive, and scalable, increasing the need for LLM-based de- fenders that can protect users→12 Aug 2026According to AMD, Arm, and Microsoft, agentic AI could push CPU-to-GPU ratios from 1:4 to even1:1In OCP APAC 2026, Tai AMD SVP of compute and enterprise AI said agents don't cut GPU demand but they just pile on a whole extra layer of orchestration, retrieval, and tool-calling work that runs on CP
TechniqueFine-tuning8 recent entries11 Aug 2026Label Granularity Skew in Federated Learning with Hierarchical Image ClassificationarXiv:2608.09236v1 Announce Type: new Abstract: Federated learning enables privacy-preserving collaboration across distributed devices without centralizing local data. However, clients may differ not →11 Aug 2026Hallucination-Free GUI Grounding via Regression-Free Layout-Aware MatchingarXiv:2608.09654v1 Announce Type: new Abstract: GUI agents are shifting from metadata-dependent large language models to purely visual multimodal large language models (MLLMs) that operate directly on→11 Aug 2026Diffusion Image Editing via Asynchronous Token DecodingarXiv:2608.09322v1 Announce Type: new Abstract: Text-guided diffusion image editing aims to modify semantic attributes of an image while preserving its identity, layout, and background. However, naive→12 Aug 2026VidForensics-M1: Meta-Detection Reinforcement Learning with Verifiable Temporal Grounding for AI-Generated Video ForensicsarXiv:2608.11201v1 Announce Type: new Abstract: Recent advances in video generation models have significantly improved the realism of synthetic videos, blurring the boundary between generated and auth→12 Aug 2026UniProbe: A Learnable Token-Level Hallucination Detector for Large VLMs using Multi-Structural Internal RepresentationsarXiv:2608.10835v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) achieve impressive visual reasoning and dialogue capabilities, yet frequently hallucinate content unsupported by th→12 Aug 2026ThinkAfford: Affordance-Centric Reasoning for Fine-Grained 3D Grounding in Cluttered ScenesarXiv:2608.10981v1 Announce Type: new Abstract: Task-driven 3D affordance grounding aims to localize the functional region in a cluttered 3D scene that enables an action specified by a natural-languag→12 Aug 2026RAG for regular users?One of the reasons I got into local LLMs was the possibility of getting answers using my own documents and books (a few hundreds) instead of having to search through them manually. However since I'm n→12 Aug 2026Certify or Refuse: A Cross-Model Map for Selective Risk Control with Coverage Floors under Covariate ShiftarXiv:2608.10893v1 Announce Type: new Abstract: Certified selective predictors attain whatever coverage they attain; operators impose an automation floor: answer at least a eta-fraction of shifted tar
TechniqueMultimodal8 recent entries12 Aug 2026Sheaf-Based Federated Representation LearningarXiv:2608.10016v1 Announce Type: cross Abstract: Heterogeneous federated systems require agents to learn and exchange informative representations despite differences in data distributions, sensing mo→12 Aug 2026Reconfiguration of pivoting cube ensembles under local sensing constraints using geometric deep learningarXiv:2509.03140v2 Announce Type: replace-cross Abstract: We demonstrate that local sensing is sufficient for effective global reconfiguration of homogeneous pivoting cube modular robots in two dimens→12 Aug 2026PBD-AG: Persistent Baseline-Delta Active Graphs with Uncertainty-Aware Inspection for Long-Horizon Service RobotsarXiv:2608.10449v1 Announce Type: new Abstract: Long-horizon service robots require persistent world models that can be built autonomously in unseen environments and revised as task-relevant objects c→12 Aug 2026MultiModal Code-Switching: Interleaving Visual Objects into Language for Explicit Object-Level AlignmentarXiv:2608.11167v1 Announce Type: cross Abstract: Existing Multimodal Large Language Models (MLLMs) predominantly rely on image-text pairs for modality alignment pretraining, mapping global image repr→12 Aug 2026LiquidAI/LFM2.5-VL-3B · Hugging FaceLFM2.5-VL-3B is a multimodal variant of LFM2.5, a family of hybrid models designed for on-device deployment. It builds on LFM2-VL-3B with further mid- and post-training. LFM2.5-VL-3B can process both →12 Aug 2026JEPA-WAM: Stage-Level Joint-Embedding Prediction for World-Action Models in Robot ManipulationarXiv:2608.10780v1 Announce Type: new Abstract: Generalist robot policies aim to map multimodal observations and linguistic task instructions to actions across diverse tasks. However, existing methods→12 Aug 2026Embodied Multimodal Grounding for Open-Vocabulary Mobile Manipulation via Semantic 3D Gaussian SplattingarXiv:2608.10756v1 Announce Type: cross Abstract: Embodied mobile manipulation requires language, visual observations, three-dimensional scene structure, and action feasibility to be aligned before ex→12 Aug 2026Conversational Orchestration for Organic 6GarXiv:2608.10714v1 Announce Type: cross Abstract: The Organic 6G vision of a network of networks spanning an edge-cloud continuum complemented by non-terrestrial resources requires, to realize its pro
TechniqueSafety8 recent entries11 Aug 2026Position: Certifiable State Integrity Should Be Built from Local Validity, Not Global ScalearXiv:2601.21249v2 Announce Type: replace Abstract: Breakthroughs in language and vision have motivated increasingly general foundation models for time series and physical dynamics, where evidence is →11 Aug 2026Decided Upstream, Written Late: Locating and Pricing the Cross-Lingual Refusal Circuit of a Multilingual MoEarXiv:2608.08032v1 Announce Type: new Abstract: Safety alignment in multilingual models is uneven: a model that reliably refuses a harmful request in English will often comply with the same request in→11 Aug 2026Beyond Hazard Resemblance: Contrastive Event Adjudication for Training-Free Video Anomaly DetectionarXiv:2608.09908v1 Announce Type: new Abstract: Video anomaly detection (VAD) aims to identify and temporally localize abnormal events in videos. Supervised methods learn anomaly decision boundaries f→11 Aug 2026Agentic AI-driven Immersive Simulation: A Knowledge-Aware Virtual Training Platform forHigh Dose Rate (HDR) BrachytherapyarXiv:2608.08163v1 Announce Type: new Abstract: The convergence of the Metaverse and Large Language Model (LLM)-based AI agent is catalyzing a shift toward autonomous, immersive, and personalized peda→12 Aug 2026Toward the Cognitive--Physical Limits of Embodied Intelligence through a World-Model-Centric Autonomous Racing AgentarXiv:2608.10618v1 Announce Type: new Abstract: Embodied artificial intelligence aims to develop agents that perceive, reason, and act through continuous interaction with the physical world. However, →12 Aug 2026The Illusion of Cross-Lingual Safety in Low-Resource LanguagesarXiv:2608.11146v1 Announce Type: new Abstract: Safety alignment in large language models (LLMs) is largely developed in English, assuming these safeguards generalize across multilingual settings. How→12 Aug 2026Easy3D-Labels: Supervising Semantic Occupancy Estimation with 3D Pseudo-Labels for Automotive PerceptionarXiv:2509.26087v5 Announce Type: replace Abstract: In perception for automated vehicles, safety is critical not only for the driver but also for other agents in the scene, particularly vulnerable roa→12 Aug 2026Certify or Refuse: A Cross-Model Map for Selective Risk Control with Coverage Floors under Covariate ShiftarXiv:2608.10893v1 Announce Type: new Abstract: Certified selective predictors attain whatever coverage they attain; operators impose an automation floor: answer at least a eta-fraction of shifted tar