Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2610.00330v1 Announce Type: cross Abstract: Long-term object search requires learning where objects usually appear from repeated but uneven observations of a changing environment. We formulate...
arXiv:2610.01999v1 Announce Type: new Abstract: Spatial reasoning benchmarks evaluate vision-language models across diverse tasks, but task-level scores do not reveal which underlying capabilities ac...
arXiv:2610.01962v1 Announce Type: cross Abstract: The ability of vision-language models (VLMs) to associate visual identities with biographical information creates a need for selective unlearning of...
arXiv:2502.14994v2 Announce Type: replace Abstract: The rapid advancement of AI-generated video poses challenges to digital authenticity and security. Current detection methods, often trained on spec...
arXiv:2602.10639v2 Announce Type: replace Abstract: Video Large Language Models (VideoLLMs) have achieved strong performance on video understanding tasks, yet existing benchmarks evaluate only what m...
arXiv:2602.14929v2 Announce Type: replace Abstract: Aligning ground-level imagery with geo-registered satellite maps is crucial for mapping, navigation, and situational awareness, yet remains challen...
arXiv:2603.26945v2 Announce Type: replace Abstract: Appearance-based gaze estimation (AGE) has achieved remarkable performance in constrained settings, yet we reveal a significant generalization gap...
arXiv:2609.32193v2 Announce Type: replace Abstract: Vision Language Action (VLA) models condition actions directly on current visual and language context, without an explicit account of how the scene...
arXiv:2609.33167v2 Announce Type: replace Abstract: We present FloodDiffusion 2 (FD2), an efficient and controllable framework that builds upon FloodDiffusion (FD1), a state-of-the-art streaming moti...
The study evaluates Jev 1.13, a non‑generative model that selects from predefined answer options, on four medical benchmarks: MetaMedQA, PubMedQA, DiagnosisArena‑MCQ, and the NEJM Case Challenges. Jev’s top‑1 accuracy matches GPT‑6 Sol with medium reasoning on PubMedQA but falls behind on MetaMedQA, DiagnosisArena‑MCQ, and NEJM cases. While Jev shows strong calibration on MetaMedQA and is fast and inexpensive, its performance on examination and complex diagnostic tasks is substantially lower, indicating the need for task‑specific validation before clinical deployment.
The paper introduces a lightweight deep learning framework that forecasts Brazilian soybean yields using only routine weather data and two simple static inputs (crop year and agro-environmental label). Across 20 seasons, transformer-based models achieved the highest accuracy, outperforming traditional ridge regression and a moving‑average baseline by nearly 48%. Ablation studies show that the static inputs and spatial expansion improve performance without adding complexity, and SHAP analysis highlights the importance of crop year and weather variables in driving yield variations.
The paper introduces a network‑based spatial context retrieval pipeline that uses pedestrian street networks and open data (OpenStreetMap, GHS‑POP) to generate compact spatial briefs for open‑weight large language models. It then builds a faithfulness benchmark that labels each model claim by its source—whether grounded in the brief or drawn from training knowledge—and tests models against planted false premises across multiple cities and model configurations. The study finds that model family and generation influence resistance to false premises more than model size, revealing dimensions of spatial reasoning not captured by traditional correctness metrics.
Lang3DSeg introduces a point‑transformer backbone for open‑vocabulary, annotation‑free 3D LiDAR segmentation, trained from scratch without geometric pre‑training. It tackles noise from 2D‑to‑3D label projections by applying a class‑priority rule and truncating projected instances at depth gaps, thereby correcting depth‑ambiguity errors. The method achieves state‑of‑the‑art results on nuScenes (52.8 % mIoU) and SemanticKITTI (41.4 % mIoU) while operating in real‑time on a single LiDAR sweep.
OneStreamer is a streaming video model that jointly learns to record evidence and respond to tasks through a shared proactive generation process. Its Proactive Hierarchical Caption Memory creates time‑grounded local‑detail captions and event summaries, while Proactive State Transition Learning reduces waiting states by supervising all output anchors. The authors also built a large OneStreamer‑1M dataset and show that a 4B model outperforms baselines on eight streaming video benchmarks, with ablations confirming the benefits of generated captions and PSTL.
DecomVoxel introduces a guided in‑situ denoising optimization that fuses 3D‑native priors with neural scene reconstruction to improve decompositional scene reconstruction. The method employs an epsilon‑based distillation loss for stable latent refinement and adaptive spatial guidance using occupied and vacant anchors with temporal annealing to reduce hallucinations and spatial drift. Experiments on Replica and ScanNet++ demonstrate that DecomVoxel outperforms state‑of‑the‑art approaches while preserving spatial layout, structural fidelity, and style‑consistent texture, yielding high‑quality textured meshes with clean topology.
The paper introduces PCSR-Bench, a benchmark of 84,373 question‑answer pairs derived from 2,600 omnidirectional images across 26 indoor environments, designed to evaluate perspective‑conditioned spatial reasoning (PCSR) in multimodal large language models (MLLMs). It reports a significant perception–reasoning gap, with accuracy dropping from 57.59% on limited field‑of‑view reasoning to as low as 0.64% on open‑ended compositional directional chains. An RL‑based diagnostic study on a 7B‑scale model shows that reward shaping can improve performance to 60.06% on a controlled task, indicating partial plasticity of PCSR capabilities.
The paper introduces GTA‑VLA, an interactive Vision‑Language‑Action framework that lets users guide robot policies with explicit visual cues such as affordance points, boxes, and traces. Unlike traditional direct sense‑to‑act models, GTA‑VLA incorporates a spatial‑visual Chain‑of‑Thought that blends human guidance with internal task planning, and couples this reasoning module with a lightweight reactive action head for efficient execution. Experiments on the SimplerEnv WidowX benchmark show a state‑of‑the‑art 81.2 % success rate, and the framework significantly improves task success under out‑of‑domain visual shifts and spatial ambiguities, demonstrating the benefit of interactive reasoning for failure recovery in embodied control.
The paper introduces the fractional Laplace neural operator (fLNO), a neural operator that embeds Volterra resolvent structures with non‑rational Laplace symbols into learned maps. It demonstrates that a single graph‑spectral layer can exactly represent the full linear Volterra solution for commuting excitation–Laplacian pairs, and establishes limits on the expressivity of finite rational realizations, showing they cannot capture non‑integer critical asymptotics. The authors also provide trainable parametrizations that enforce stability margins, a graphon‑transfer theorem, and empirical results on benchmark data, Chilean aftershock sequences, and renewal models, highlighting the fLNO’s ability to recover branching coordinates with few parameters while maintaining stability.
Build2SPARQL is a large-scale benchmark dataset for translating natural-language questions into SPARQL queries over building knowledge graphs. The dataset is generated by a KG‑grounded pipeline that produces 6,136 executable SPARQL queries and 30,680 corresponding natural-language questions across six query-pattern families and five vocabulary registers, covering 201 building KGs. Human validation shows high semantic fidelity, naturalness, and operational plausibility, and retrieval‑augmented evaluation demonstrates significant accuracy gains for open‑weight language models.
JusticeAxis is a new benchmark that formalizes legal judgment as a reference‑anchored task, requiring a single decision tied simultaneously to the statute and the surrounding circumstances. It comprises 256 real‑world criminal cases from 18 countries, each with audio, image, and text evidence, and three lawyer‑written judgments per case: the recorded judgment and two failure judgments. The authors also introduce JusticeAgent, a modular system that first establishes facts and then applies the law, with skills distilled from execution trajectories and validated under Bayesian credible bounds. Experiments reveal that open‑weight backbones tend to drift toward unsupported grounds while frontier models default to statutory interpretations, and that JusticeAgent can effectively plug into commercial systems.