TechniqueRLHF / Alignment8 recent entries14 Oct 2026Beyond RMSE and Granger Gain: Multi-Horizon Forecast-Error Entropy for Nonlinear Predictive CouplingarXiv:2610.18390v1 Announce Type: cross Abstract: We investigate whether the past of an auxiliary time series provides predictive information about a target beyond that contained in the target's own h→14 Oct 2026Benchmarks Are Not Atomic: Composition-Aware LLM Evaluation using BenchHubarXiv:2506.00482v2 Announce Type: replace Abstract: LLM benchmarks are often treated as coherent measurement units, yet they are heterogeneous collections of instances spanning diverse domains, skills
TechniqueRAG8 recent entries14 Oct 2026Heading Hierarchy Reconstruction for Complex and Long Documents with Level-Wise Multimodal MemoryarXiv:2610.18238v1 Announce Type: new Abstract: Vision-language models (VLMs) have been widely adopted for document parsing and optical character recognition (OCR), as they can accurately extract page→14 Oct 2026Hallucination-aware Faithful Reasoning in Remote SensingarXiv:2610.18369v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have demonstrated promising capabilities for remote sensing reasoning, yet they frequently generate visually un→14 Oct 2026EvoSpatial: Experience-Driven Skill and Tool Evolution for Spatial Reasoning AgentsarXiv:2610.16679v1 Announce Type: new Abstract: Tool-augmented vision-language agents compose perception and measurement to reason about spatial relationships, but effective execution also requires tr→14 Oct 2026Elephant in the Fridge: Constant-Memory Frame Packing for Long Video UnderstandingarXiv:2610.16118v1 Announce Type: new Abstract: Hour-long videos, streaming feeds, and movie-length content are pushing vision-language models (VLMs) past their breaking point -- the standard recipe o→14 Oct 2026DuSRFlow: Dual-Lens Super-Resolution via Parallax-Aware Flow Estimation and Complementary Reference WarpingarXiv:2610.14630v1 Announce Type: new Abstract: Dual-lens super-resolution (DuSR) aims to enhance a wide-angle low-resolution (LR) image by exploiting a telephoto reference (Ref) image. A central chal→14 Oct 2026Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language ModelsarXiv:2506.17585v4 Announce Type: replace-cross Abstract: Large language models can answer questions correctly and still hallucinate their citations. Most citation systems address this by retrieving d→14 Oct 2026An Agentic AI System for Multi-Framework Communication CodingarXiv:2512.08659v2 Announce Type: replace-cross Abstract: Clinical communication is central to patient outcomes, yet large-scale human annotation of patient-provider conversation remains labor-intensi→14 Oct 2026A Persian Vision-Language-Action Dataset and Benchmark for Ambiguity- and Infeasibility-Aware Instruction-to-Plan GroundingarXiv:2610.15666v1 Announce Type: new Abstract: Converting natural-language instructions into executable action plans conditioned on a scene image is a core capability for embodied human-robot interac
TechniqueAgents8 recent entries14 Oct 2026APT: Feedback-Driven Agentic Post-Training for Text-to-Image GenerationarXiv:2610.18097v1 Announce Type: new Abstract: Post-training is crucial for improving text-to-image models, yet existing pipelines typically rely on manually curated training data and fixed training →14 Oct 2026An Agentic AI System for Multi-Framework Communication CodingarXiv:2512.08659v2 Announce Type: replace-cross Abstract: Clinical communication is central to patient outcomes, yet large-scale human annotation of patient-provider conversation remains labor-intensi→14 Oct 2026AI Discovery in Combinatorics: From Problems to Solutions and Back to Bigger ProblemsarXiv:2610.16555v1 Announce Type: cross Abstract: We introduce qtBench, a benchmark of 29 open problems in algebraic combinatorics. These problems ask for a simple combinatorial algorithm that explain→14 Oct 2026Agentic Data Engineering for LLMs: System Design and a Controlled Empirical StudyarXiv:2610.14238v1 Announce Type: cross Abstract: LLM data engineering requires iterative experimentation to determine how data selection, rewards, and curricula affect model learning, making it a nat→14 Oct 2026AffectWorld: Benchmarking Emotion-Driven Future World PredictionarXiv:2610.18305v1 Announce Type: new Abstract: The world encompasses both physical environments and human actors. Predicting its evolution requires understanding both physical laws and how emotions s→14 Oct 2026A Reinforcement Learning Framework for Safety-Aware Haptic Shared Control in Surgical RoboticsarXiv:2610.15422v1 Announce Type: new Abstract: Haptic shared control in surgical robotics combines human-side and robot-side forces at a shared end effector while preserving operator involvement. How→14 Oct 2026A Persian Vision-Language-Action Dataset and Benchmark for Ambiguity- and Infeasibility-Aware Instruction-to-Plan GroundingarXiv:2610.15666v1 Announce Type: new Abstract: Converting natural-language instructions into executable action plans conditioned on a scene image is a core capability for embodied human-robot interac→14 Oct 2026A Gated Catchment Hydrology Model (GCHM) for Physically-Interpretable Rainfall-Evapotranspiration-Runoff Simulation Across Diverse Hydroclimatic RegimesarXiv:2610.14493v1 Announce Type: new Abstract: Recent advances in machine learning have improved rainfall-runoff prediction, yet most data-driven models remain difficult to interpret and do not expli
TechniqueFine-tuning8 recent entries14 Oct 2026Building age estimation based on widely available multi-source1 geospatial dataarXiv:2610.16320v1 Announce Type: new Abstract: Building age is fundamental for urban infrastructure safety, operation, and planning, as it directly affects structural safety, and sustainable developm→14 Oct 2026Bidirectional Adaptive Transformers for Multimodal Anomaly DetectionarXiv:2610.14598v1 Announce Type: new Abstract: The effective integration of features derived from RGB images and 3D point clouds presents a substantial challenge in the field of multimodal anomaly de→14 Oct 2026Benchmarking Self-Supervised 3D Medical Vision Foundation Models and Transferability EstimationarXiv:2610.17573v1 Announce Type: new Abstract: Self-supervised pretraining has expanded the pool of 3D medical foundation models, but published evaluations use different datasets, endpoints and fine-→14 Oct 2026BaT-SAM: Introducing Inductive Bias into SAM via a Mixture of Convolutional Experts for Brain Tumor SegmentationarXiv:2610.15330v1 Announce Type: new Abstract: Accurate brain tumor segmentation from magnetic resonance imaging (MRI) is essential for diagnosis and treatment planning; however, manual delineation i→14 Oct 2026Barycentric Anchored Weight Search for Robust Model MergingarXiv:2610.14017v1 Announce Type: cross Abstract: We propose Barycentric Anchored Search, a post-hoc weight-space procedure for improving fine-tuned vision models under distribution shift without addi→14 Oct 2026BARTER: Compact Dynamic Sparse Training with Standard Dense KernelsarXiv:2610.16147v1 Announce Type: new Abstract: Dynamic sparse training (DST) aims to reduce training costs while maintaining accuracy. Existing DST methods mask out parameters but keep matrix dimensi→14 Oct 2026Auditing Failure Attribution: Label Predictability and Judge BehaviorarXiv:2610.17747v1 Announce Type: cross Abstract: Failure-attribution benchmarks ask an LLM judge which step or agent caused a failure. A high score should mean the judge checked the faulty step again→14 Oct 2026Agaram 2.5B: The First Tamil-First Language Model Trained from Scratch with Tool Calling. A Playbook for Under-Represented LanguagesarXiv:2610.18420v1 Announce Type: cross Abstract: We trained Agaram 2.5B, a 2.5-billion-parameter Tamil-English language model, from scratch on about 50 billion tokens (58% Tamil, the rest English, ma
TechniqueMultimodal8 recent entries14 Oct 2026Benchmarking Interaction-Oriented Aerial Mobility across Heterogeneous EnvironmentsarXiv:2610.18381v1 Announce Type: new Abstract: Aerial mobile manipulation requires unmanned aerial vehicles (UAVs) to traverse heterogeneous environments such as indoor and outdoor domains, and conne→14 Oct 2026Attribute-Centric Vision-Language Alignment for Fine-Grained Gait UnderstandingarXiv:2610.14589v1 Announce Type: new Abstract: Walking sequences reveal human-interpretable attributes related to body structure, posture, and motion. Gait attribute recognition provides a concrete r→14 Oct 2026APT: Feedback-Driven Agentic Post-Training for Text-to-Image GenerationarXiv:2610.18097v1 Announce Type: new Abstract: Post-training is crucial for improving text-to-image models, yet existing pipelines typically rely on manually curated training data and fixed training →14 Oct 2026AffectWorld: Benchmarking Emotion-Driven Future World PredictionarXiv:2610.18305v1 Announce Type: new Abstract: The world encompasses both physical environments and human actors. Predicting its evolution requires understanding both physical laws and how emotions s→14 Oct 2026AERR-Nav: Adaptive Exploration-Recovery-Reminiscing Strategy for Zero-Shot Object NavigationarXiv:2603.17712v1 Announce Type: cross Abstract: Zero-Shot Object Navigation (ZSON) in unknown multi-floor environments presents a significant challenge. Recent methods, mostly based on semantic valu→14 Oct 2026A text-guided vision model for enhanced recognition of small instancesarXiv:2602.19503v2 Announce Type: replace Abstract: As drone-based object detection technology continues to evolve, the demand is shifting from merely detecting objects to enabling users to accurately→14 Oct 2026A Persian Vision-Language-Action Dataset and Benchmark for Ambiguity- and Infeasibility-Aware Instruction-to-Plan GroundingarXiv:2610.15666v1 Announce Type: new Abstract: Converting natural-language instructions into executable action plans conditioned on a scene image is a core capability for embodied human-robot interac→14 Oct 2026A Multi-Task Deep Learning Framework for Pose-Invariant Face Recognition and Facial Landmark LocalizationarXiv:2610.16849v1 Announce Type: new Abstract: Face recognition systems often experience performance degradation under large pose variations due to changes in facial appearance and visibility of disc
TechniqueSafety8 recent entries14 Oct 2026CAG-WAM: Causal Action-Gain World Action Models for Robot ManipulationarXiv:2610.14720v1 Announce Type: new Abstract: World Action Models (WAMs) combine action generation with future prediction, allowing predicted futures to support action evaluation and robot decision →14 Oct 2026Building age estimation based on widely available multi-source1 geospatial dataarXiv:2610.16320v1 Announce Type: new Abstract: Building age is fundamental for urban infrastructure safety, operation, and planning, as it directly affects structural safety, and sustainable developm→14 Oct 2026Beyond Policy Rollouts: Embedding-Space Directional Exploration with Anchored Noise for LLM RLVRarXiv:2610.16105v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) typically uses small rollout groups per prompt, where repeated sampling from the same policy can y→14 Oct 2026AnyRank: Reliable Anytime Policy Ranking via Sequential TestingarXiv:2610.14603v1 Announce Type: new Abstract: Due to the high cost of hardware experiments, robot policies are predominantly evaluated by comparing their empirical performance on a limited number of→14 Oct 2026AdaGamma: State-Dependent Discounting for Temporal Adaptation in Reinforcement LearningarXiv:2605.06149v2 Announce Type: replace Abstract: The discount factor in reinforcement learning controls both the effective planning horizon and the strength of bootstrapping, yet most deep RL metho→14 Oct 2026Across Viewpoints and Time: Trajectory-Generalizable Physical Attacks on World Models and Video Understanding ModelsarXiv:2610.15343v1 Announce Type: new Abstract: World models and video understanding models are increasingly deployed in dynamic visual environments, yet their robustness to physical adversarial threa→14 Oct 2026A Reinforcement Learning Framework for Safety-Aware Haptic Shared Control in Surgical RoboticsarXiv:2610.15422v1 Announce Type: new Abstract: Haptic shared control in surgical robotics combines human-side and robot-side forces at a shared end effector while preserving operator involvement. How→14 Oct 2026A CaLLM Judge is a Better Judge: Mitigating Bias in LLM-as-a-judgearXiv:2610.18108v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as judges to predict which of two candidate answers a human evaluator would prefer, providing a scala