MultiView-Bench is a diagnostic benchmark designed to evaluate vision-language models' ability to integrate observations across multiple viewpoints into a coherent, world-centric 3D mental model. Current VLMs excel at single-view 2D tasks but struggle with 3D spatial relations and cross-view aggregation. The authors propose ViewNavigator, a multi-agent framework that actively selects informative viewpoints and fuses multi-view evidence, achieving 3-5x performance improvements on the benchmark.

A study in Côte d'Ivoire comparing very high resolution (0.5m) with decametric satellite imagery for cocoa mapping finds VHR achieves F1=0.92, while foundation-model embeddings like TESSERA (F1=0.86) offer scalable alternatives. Performance differences increase in fragmented landscapes.

A new study shows that Vision Transformers (ViTs) can learn Gestalt-like figure-ground cues such as surroundedness, convexity, and symmetry from natural images. Testing 25 ViT models, the researchers found robust encoding of surroundedness and convexity, while symmetry cues only worked for uniformly colored regions. The work demonstrates that Gestalt cues can be learned from natural scene statistics and positions ViTs as a model system for studying perceptual organization.

We describe our entry to the ICIP 2026 Grand Challenge on Extreme In-the-Wild License Plate Super-Resolution (XLPSR), which scored 9.73 wECR on the public validation leaderboard. The system pairs a Hybrid Attention Transformer super-resolution (HAT) front-end with an ensemble of two scene-text recognisers (PARSeq-S and CLIP4STR-B) and a confidence-weighted character-voting scheme that abstains on uncertain positions. Our pipeline runs in 1.7 s per sequence on RTX 3090, well under the 60 s/sequence Docker budget.

Lume-Palette framework achieves spatially controllable multi-view indoor scene relighting by decoupling the process into illumination distillation and illumination casting, enabling fine-grained 3D light control while maintaining multi-view consistency.

This paper introduces Mixture of Probes (MoP), a framework that enables multimodal LLMs to effectively leverage auxiliary modalities only available during training. MoP uses a structured probing mechanism to extract information from intermediate representations, and MoP-X training strategy with probe disentanglement loss. Experiments show up to 65% relative improvement over baselines.

StereoSplat+ is a diffusion-enhanced feed-forward framework that enables causal reconstruction from a single stereo pair without requiring multi-view observations. The method includes a stereo Gaussian estimator and a progressive inference scheme, improving novel-view rendering quality and geometry accuracy on the KITTI-360 dataset.

This research examines the technical and ethical challenges of automated keyword extraction in crowdsourced collections, using the University of Oxford's Second World War archive as a case study. It compares three NLP approaches and finds that while promising, no method is perfect; open-weight extractive models are recommended over generative AI for responsible deployment.

This paper explores machine learning for automatic thematic indexing of large literary corpora, using Voltaire's works as a test case. The best model, a 4-bit quantized Mistral, achieves F1 scores up to 0.67, highlighting the potential of automated indexing.

Research shows that small hyperbolic language models can exhibit creativity, honesty, and designed forgetting, offering a small-model route to trustworthy companion AI. These models include a behavioral auditor, a creative frame-seeder, and a memory operating system.

This paper introduces letter lemmatization using one-to-one RNNs with self-supervision to reverse character-set simplifications, achieving half CER recovery from just 20 text lines. It also employs Banded RNNs for abbreviation expansion in medieval charters and presents a heuristic for semantic similarity between character sets, along with a Python library.

This study analyzes weight spectra of eleven GPT-2-style pretrained models, finding shared depth trends such as increasing scale and spectral concentration in residual-writing matrices. The authors construct initialization schemes that mimic these spectral patterns, but find no performance advantage over standard methods. Pretrained weight reuse remains competitive, suggesting that coarse spectral matching is insufficient for effective reuse; richer information is needed.

This study explores using GPT-4o with Retrieval-Augmented Generation (RAG) to automate fundamental analysis by processing company reports, macroeconomic data, and SEC filings. The system scanned 9 companies for 4 weeks, producing investor briefs evaluated by 9 individual investors.

Knowledge graphs (KGs) often contain factual errors from automatic construction. AgentKGV proposes an agentic LLM-RAG framework with dynamic routing and iterative query rewriting, enhanced by a two-stage training strategy (distillation-based SFT and trajectory-level GRPO) for improved accuracy and cost efficiency. On the T-REx benchmark, macro-F1 improves by 14.9 percentage points over single-turn RAG, with search calls halved.

A new study questions the robustness of Emergent Misalignment (EM) in language models. While replicating EM, the authors find that misalignment and realignment are highly sensitive to superficial dataset characteristics, such as response-length differences, and previously reported representational phase transitions do not consistently correlate with behavioral misalignment. This suggests current evidence for EM is less robust than claimed, calling for more rigorous evaluation protocols.

HALO is a hybrid adaptive latent-refinement method that improves frozen pretrained language models by combining a coarse refinement stage with selective second-stage latent refinement based on token scoring. It achieves the best average performance on MMLU-Pro and GPQA-Diamond while using fewer compute steps than fixed baselines.

A new GPU inference method for LLMs with moderate sparsity (around 50%) is proposed, using a three-layer matrix storage format that enables sparse tensor cores and CUDA cores to jointly accelerate sparse matrix multiplication. It is the first to outperform dense matrix multiplication on modern HBM-equipped GPUs, achieving up to 1.64x kernel-level speedup over SpInfer and 1.41x end-to-end speedup over FlashLLM.

High-quality data drives machine learning, but pricing data products is challenging due to near-zero marginal cost and unpredictable revenue. Traditional pricing methods fail; the sales comparison approach lacks benchmarks. Researchers introduce DaDaDa, the first dataset for data product pricing, containing metadata on 16,147 products from 9 major marketplaces. It enables training pricing models, establishing benchmarks, and supports classification and retrieval tasks. Experiments show effectiveness.

Federated continual learning (FCL) evaluates how distributed clients learn from changing data streams while retaining previously learned knowledge. Existing evaluations are difficult to compare because they often change datasets, task splits, client data splits, task orders, backbones, memory assumptions, and reporting rules simultaneously. We introduce HERO, a heterogeneity-aware benchmark library for FCL. HERO builds benchmark streams by separating three choices that are often coupled, namely the task split, the client data split, and the client task sequence. In HERO-Core, α controls client data skew and ρ controls task-order mismatch. We evaluate representative FCL methods on CIFAR-100 and TinyImageNet using final average accuracy, average forgetting, and bottom-10% client accuracy. R…

This paper proposes LieBN, a framework for Riemannian Batch Normalization over Lie groups, leveraging left- and right-invariant metrics for theoretical guarantees. It instantiates across nine geometries, including SPD manifold, rotation matrices, and full-rank correlation matrices, with extensive experimental validation.

Director is a new distributed MoE serving system that minimizes end-to-end latency through prediction-driven, online expert placement. It uses a lightweight cascaded predictor or low-bit quantized replica for expert activation patterns, an online migration module with near-zero downtime, and a relaxation-based optimizer that achieves a (1+ε) approximation ratio in polynomial time. Experiments show an 11–55% reduction in latency for popular MoE models.

This paper introduces Reward Transport, which leverages optimal transport coupling to align a scalar noise-space coordinate with molecular rewards during training, enabling controllable generation at inference by simply adjusting this coordinate without requiring an oracle, reward model, gradient guidance, or additional computation. Experiments on ZINC-250K and GuacaMol demonstrate monotonic control of logP and consistent QED control, ruling out generic size bias, and the method is complementary to classifier-free guidance.

We propose StickyMoE, a differentiable routing consistency loss that penalizes abrupt expert switches between adjacent tokens during training, enabling memory-efficient inference on edge devices. Experiments show up to 60% reduction in expert switch rate with less than 4% perplexity degradation.

This paper introduces signed symmetric quantization for few-bit integers, addressing clipping errors from standard symmetric quantizers while avoiding the runtime penalty of asymmetric quantization. The method places the extra negative value on the dominant outlier tail, achieving better perplexity and accuracy on large language models at no extra inference cost.

iLENS is an interpretable LLM-guided mixture-of-experts framework for survival prediction in Alzheimer's disease conversion. It synthesizes structured neuroimaging measurements and unstructured information to guide expert routing, offering competitive predictive performance, patient subtyping, and transparent biologically grounded rationales, bridging high-performance survival analysis and interpretable clinical decision support.

This paper proposes a unified approach to explain the mechanism of knowledge distillation (KD) in large language models (LLMs). By decomposing the output into interactions, it reveals that KD commonly sparsifies interactions—student models retain fewer interactions for inference. Performance differences stem from handling complex interactions, leading to a novel Complex Interaction Penalty (CIP) loss that improves various KD methods consistently.

KV-PRM is an efficient process reward model that eliminates text re-encoding by directly using the KV cache from LLM generation, reducing scoring cost from O(L²) to O(L). It matches or outperforms text-PRMs on benchmarks with up to 5000x FLOPs reduction, 37x latency reduction, and 34x memory reduction.

MedRealMM is a large-scale benchmark built from de-identified patient-doctor interactions from a nationwide Chinese internet hospital. It includes 5,620 multimodal cases across 64 departments and uses a Multimodal Clinical Challenge Point (MCCP) extraction framework to create standardized next-response generation tasks. Evaluation of 19 LLMs shows that image information is critical for reliable clinical performance, and current frontier models, while meeting positive clinical criteria comparably to physicians, trigger more negative criteria, highlighting safety-sensitive error avoidance as a key bottleneck.

The L-MAD framework systematically evaluates multi-agent debate structures and aggregation methods in Legal Textual Entailment. By assigning expert personas, it improves upon single-agent baselines by up to 8%. Increasing agent population reduces inconsistency and improves accuracy, but extending discussion rounds induces over-deliberation drift where agents reinforce each other's mistakes. The findings outline practical boundaries for deploying multi-agent systems in high-stakes legal reasoning.

This paper introduces a neuro-agentic control framework that couples an LLM planner with a time-series foundation model (TimesFM) using counterfactual physics injection to ensure physics-grounded autonomous defense, outperforming LSTM and TCN on SWaT dataset with zero hallucinated actions.