NTIRE 2026 Low-light Enhancement: Twilight Cowboy Challenge

This paper presents a review of the NTIRE 2026 Low-light Enhancement: Twilight Cowboy Challenge. The objective of the competition was to merge a set of misaligned smartphone images in the raw domain, captured in low-light conditions, into a single, clean image. Introduced setup simultaneously addresses two problems of low-light photography: visual degradations such as high noise and mixed scene illuminants, and the geometric inconsistencies caused by hand movement during multi-frame capture. To advance research in low-light and nighttime computational photography, a challenging dataset was collected comprising 585 real-world scenes, spanning indoor low-light and outdoor nighttime conditions, for training and benchmarking participant solutions. The competition employed a three-stage evaluation protocol: automatic validation via the CodaBench platform in stages one and two, followed by blind assessment on a private test set for the final ranking. Ten teams surpassed the established baseline, achieving improvements of up to +6.49 dB in PSNR and +0.0101 in SSIM, thereby establishing new state-of-the-art performance for burst-based low-light image enhancement. These results demonstrate significant progress in handling real-world noise, motion, and illumination variability in the low-light setting. Comprehensive results, leaderboards, and additional information are publicly available at https://nightimaging.org.

Learning When to Trust via Selective Context Preference Optimization

Language models increasingly condition their answers on external signals, and a single misleading one can turn a correct answer wrong. The obvious remedy, training models to resist such signals, hides a failure mode: a model that ignores all context looks robust yet is useless when the context is worth trusting. We recast the problem as selective trust and introduce MIST, a human-annotated benchmark that renders each reasoning item under four matched conditions (clean, misleading, correct-context, and irrelevant-context), together with SC2W, a paired metric counting how often a misleading signal flips a clean-correct answer to wrong. Across a comprehensive benchmark study, we observe that such a susceptibility is universal. We then propose SCOPE, which mines clean-correct/misleading-wrong failures and optimizes a standard Direct Preference Optimization (DPO) objective over matched preference pairs balanced equally across all four conditions, rather than over misleading items alone. Our approach substantially reduces SC2W on popular open-sourced models while preserving accuracy when the added context is clean, correct, or irrelevant. With this work, we argue that models should be judged on selective trust, not on resistance alone.

Quo Vadis, World Modeling?

Continually improving agents require dynamic interaction feedback beyond static supervision, yet direct real-environment interaction is costly, slow, unsafe, and hard to parallelize. World modeling offers a natural intermediate proxy that allows agents to query lower-cost, more controllable feedback before committing to real actions. Classical world models instantiate this proxy primarily through future physical-state prediction, a formulation useful yet narrow for agents that require actionable feedback beyond raw state transitions. In this work, we conceptualize Agent-Centric Interactive World Proxies, shifting the fundamental paradigm from physical state transitions to agent-usable information transitions, such as execution outcomes, retrieved experiences or skills, and verification signals, broadening the scope of world modeling to provide versatile feedback for continually improving agents. To systematically map this design space, we organize world proxies into six functional forms based on their feedback modalities: dynamics, spatial, execution, memory/experience, skill, and reward/verification proxies, which together characterize the primary ways world modeling serves agent improvement. We further analyze how these proxies empower agents across three progressive levels: L.1 Inference-Time Guidance, where proxy outputs enrich in-context information for superior decisions; L.2 Training-Time Optimization, where proxy outputs yield rewards, critiques, or synthetic rollouts for policy learning; and L.3 Agent-Proxy Co-Evolution, where real-environment evidence continuously updates both the proxy and the agent for co-evolution. Ultimately, this work recasts world modeling into an agent-centric paradigm, establishing a roadmap for building world proxies that empower agents to plan better, learn faster, and evolve continually.

Data Pyramid for Embodied Manipulation

Multimodal foundation models learned to see and to speak by consuming the whole internet. Embodied agents admit no such shortcut, since they require data that couple observations with physical states and actions. These signals can be provided, to varying degrees, by multiple data sources. In this work, we organize the embodied data ecosystem as a "pyramid" spanning five complementary sources: real-robot data, UMI-style data, egocentric and exocentric data, simulation data, and general vision-language data. We organize the pyramid around the tension between scalability and robot alignment, and further characterize each source in terms of data quality, diversity, reusability, and physical fidelity. We then analyze recent embodied foundation models through the lens of their data recipes, examining how different sources are selected, aligned, and mixed during pretraining. For embodied brain models, vision-language-action models, and world-action models alike, we relate data composition to capabilities in perception, reasoning, planning, action generation, and world prediction. We close by discussing six open challenges: building large-scale tactile datasets, collecting failure and recovery data, developing scalable data-collection pipelines, aligning actions across embodiments, leveraging egocentric data for dexterous manipulation, and designing principled data recipes for robot learning. We hope this work paves the foundation for the design of next-generation embodied systems.

Token-Wise Latent Streaming from Slow Reasoners to Fast Planners for Dynamic Vision Language Navigation

Vision-Language Navigation in dynamic, human-centric environments exposes a fundamental tension: linguistic reasoning is slow and deliberative, whereas safe, socially compliant planning should be instant and reactive. The resulting observation staleness is safety-critical: a maneuver chosen during inference can already be unsafe by the time it executes. We observe that, long before a VLM finishes its inference, its intermediate hidden states already encode action-relevant intent. We propose SPARK-VLN, a dual-system framework for dynamic social VLN that streams the slow VLM reasoner's knowledge to a fast flow-matching expert planner throughout token generation, providing fresh and evolving guidance during inference. This design is realized by three modules: a Token-Wise Hidden Streamer that extracts intermediate hidden states along the token generation process, a Sequence-to-Slot Latent Bridge that projects them into fixed-size latent slots, and an Evolving Latent Conditioner that infuses them into the expert planner. We also introduce a human-centric benchmark suite for dynamic social vision-language navigation that keeps pedestrians and the robot active throughout inference and reports navigation success, social compliance, human collisions, and explicit staleness statistics. Across these settings, SPARK-VLN mproves navigation success and social compliance while sustaining inference efficiency. Webpage: https://hutslib.github.io/SPARK-VLN/.

Semantic-Aware, Physics-Informed, Geometry-Grounded Weather Video Synthesis

Weather synthesis aims to add weather effects to input videos while preserving scene identity, structure, and motion. The key limitation of existing methods is the lack of diversity in weather appearance and effective control over weather dynamics (e.g., temporal evolution and particle motion). Most approaches rely on text prompts, which are inherently underspecified and often fail to produce detailed weather characteristics. Additionally, general-purpose video editors optimized for clean and aesthetic outputs tend to suppress heavy weather phenomena, making dense particle effects difficult to generate. To address these, we propose a Semantic-Aware, Physics-Informed, and Geometry-Grounded framework that steers an off-the-shelf video editor to synthesize diverse global appearances and detailed particle dynamics. We factorize the synthesis into three conditional signals, so that each provides a distinct and stable source of guidance: semantics specifies what the weather should look like, dynamics governs how it evolves over time, and geometry determines where it should appear in the scene. Specifically, we introduce (1) semantic-aware appearance anchoring to establish the target appearance from scene semantics and user input; (2) physics-informed dynamic simulation to generate particle effects by simulating a Gaussian-represented particle field under gravity, wind, and turbulence; and (3) geometry-grounded video synthesis to align the simulated particles with target scene geometry and synthesize the final video. Experiments demonstrate that our method produces diverse, physically and visually realistic weather effects. Furthermore, we show that our synthesized data significantly improves the robustness of autonomous driving semantic segmentation under adverse weather conditions. Project page: https://jumponthemoon.github.io/w-crafter/.

DanceOPD: On-Policy Generative Field Distillation

Modern image generation demands a single model that unifies diverse capabilities, including text-to-image (T2I), local editing, and global editing. However, these capabilities are rarely naturally aligned and often conflict. For instance, editing tends to degrade T2I performance, while global and local editing interfere with each other. Consequently, effectively composing these capabilities has become a central challenge for image generation model training. To tackle this, we introduce DanceOPD, an on-policy generative field distillation framework for flow-matching models that routes each sample to one capability field, queries one low-noise student-induced state, and trains with a simple velocity MSE objective. With each capability source defined as a velocity field over the shared flow state space, the student learns from fields queried on its own rollout states to compose expert capabilities. This formulation also absorbs operator-defined fields such as classifier-free guidance. Comprehensive experiments on T2I, editing, realism-field absorption, and CFG absorption show that our approach improves multi-capability composition, strengthening target capabilities while preserving anchor generation quality. We believe this work establishes a practical route for generative field distillation in flow-matching models.

Do Time Series Foundation Model Benchmarks Hide Regime-Dependent Failures? Evidence from Traffic Speed Forecasting

Standard benchmarks evaluate time series foundation models (TSFMs) using aggregate metrics, but these can mask severe failures in critical operating regimes. We introduce regime-stratified evaluation and apply it to three TSFMs on two standard traffic speed benchmarks. Traffic exhibits abrupt regime switching between free-flow and congested states, producing bimodal speed distributions during transitions. When we stratify by traffic regime, both accuracy and prediction-interval coverage degrade sharply during transitions: transition-regime MAE reaches 11 mph (versus 3 mph overall), and empirical coverage of 90% prediction intervals drops as low as 55%. These failures are invisible in aggregate metrics because free-flow observations dominate the sample. A simple historical conditional baseline (sampling from per-sensor training distributions) achieves better transition coverage than any TSFM, but has far worse overall accuracy. We propose bimodal mixture augmentation (BMA), a post-hoc method that combines TSFM forecasts with historical distributional knowledge, approaching the historical baseline's transition coverage while preserving the TSFM's accuracy. Our results suggest that TSFM benchmarks should incorporate regime-aware evaluation to surface failures that aggregate metrics hide.

EventDrive: Event Cameras for Vision-Language Driving Intelligence

Event cameras sense the world through asynchronous brightness changes with microsecond latency and high dynamic range, offering motion fidelity far beyond frame-based sensors and capturing temporal structure that conventional exposures often miss. These properties make events a powerful complement to RGB in autonomous driving, especially under blur, glare, and rapid motion, where frame-based perception can become unreliable. However, existing event-aware vision-language models remain limited to generic perception and do not reveal how event sensing contributes to reasoning and decision-making across the full driving loop. We present EventDrive, a large-scale benchmark and model suite that unifies event streams, RGB frames, and language supervision across four core dimensions: Perception, Understanding, Prediction, and Planning, covering captions, structured QA, grounding, motion-state recognition, trajectory forecasting, and planning tasks. Building on this foundation, EventDrive-VLM introduces a multi-horizon event pyramid and a temporal-horizon mixture-of-experts module to adaptively encode and fuse asynchronous and frame-based information for downstream reasoning. Comprehensive evaluation across diverse tasks shows that event streams provide substantial gains in temporal precision, motion awareness, and robustness, bringing event sensing into the center of driving intelligence.

Beyond Accuracy: Measuring Bias Acknowledgment in Chain-of-Thought Reasoning for Responsible AI Evaluation

Reasoning models are increasingly used in settings where the final answer is not the only object of review: educational tools may show students intermediate steps, decision-support systems may require human oversight, and audit workflows may inspect traces for misleading or biased input. In such settings, two responses can receive the same final-answer score while differing in whether the trace explicitly flags injected biasing content. Accuracy-only evaluation collapses these cases. We study this gap as a measurement blind spot for responsible evaluation and introduce a minimal trace-level diagnostic with two axes: \emph{susceptibility} (whether the bias breaks a previously correct answer) and \emph{acknowledgment} (whether the trace contains a rubric-defined surface reference to the injected content). Across thousands of biased GSM8K trials, GPT-4o and Claude Sonnet~4 have similar susceptibility rates ($1.3\%$ vs.\ $1.2\%$) but substantially different acknowledgment rates ($13.0\%$ vs.\ $75.0\%$) under the same rubric.