Outcome-reward reinforcement learning (RL) is a common--and increasingly significant--way to refine the step-by-step reasoning of multimodal large language models (MLLMs). In the multiple-choice setting--a dominant format for multimodal reasoning benchmarks--the paradigm faces a significant yet often overlooked obstacle: unfaithful trajectories that guess the correct option after a faulty chain of thought receive the same reward as genuine reasoning, which is a flaw that cannot be ignored. We propose Self-Consistency Sampling (SCS) to correct this issue. For each question, SCS (i) introduces small visual perturbations and (ii) performs repeated truncation-and-resampling of an initial trajectory; agreement among the resulting trajectories yields a differentiable consistency score that down-weights unreliable traces during policy updates.

In this paper, we study the robustness of classical deep hedging strategies under distributional shifts by leveraging the concept of adversarial attacks. We first demonstrate that standard deep hedging models are highly vulnerable to small perturbations in the input distribution, resulting in significant performance degradation. Motivated by this, we propose an adversarial training framework tailored to increase the robustness of deep hedging strategies. Our approach extends pointwise adversarial attacks to the distributional setting and introduces a computationally tractable reformulation of the adversarial optimization problem over a Wasserstein ball. This enables the efficient training of hedging strategies that are resilient to distributional perturbations. Through extensive numerical experiments, we show that adversarially trained deep hedging strategies consistently outperform their classical counterparts in terms of out-of-sample performance and resilience to model misspecification. Additional results indicate that the robust strategies maintain reliable performance on real market data and remain effective during periods of market change. Our findings establish a practical and effective framework for robust deep hedging under realistic market uncertainties.1

Objective gait assessment in Parkinson's Disease (PD) is limited by the absence of large, diverse, and clinically annotated motion datasets. We introduce CARE-PD, the largest publicly available archive of 3D mesh gait data for PD, and the first multi-site collection spanning 9 cohorts from 8 clinical centers. All recordings (RGB video or motion capture) are converted into anonymized SMPL meshes via a harmonized preprocessing pipeline. CARE-PD supports two key benchmarks: supervised clinical score prediction (estimating Unified Parkinson's Disease Rating Scale, UPDRS, gait scores) and unsupervised motion pretext tasks (2D-to-3D keypoint lifting and full-body 3D reconstruction). Clinical prediction is evaluated under four generalization protocols: within-dataset, cross-dataset, leave-one-dataset-out, and multi-dataset in-domain adaptation. To assess clinical relevance, we compare state-of-the-art motion encoders with a traditional gait-feature baseline, finding that encoders consistently outperform handcrafted features. Pretraining on CARE-PD reduces MPJPE (from 60.8 mm to 7.5 mm) and boosts PD severity macro-F1 by 17 percentage points, underscoring the value of clinically curated, diverse training data. CARE-PD and all benchmark code are released for non-commercial research at https://neurips2025.care-pd.ca.

Recent advancements in generative models have enabled high-fidelity text-to-image generation. However, open-source image-editing models still lag behind their proprietary counterparts, primarily due to limited high-quality data and insufficient benchmarks. To overcome these limitations, we introduce ImgEdit, a largescale, high-quality image-editing dataset comprising one million carefully curated edit pairs, which contain both novel and complex single-turn edits, as well as challenging multi-turn tasks. To ensure the data quality, we employ a multi-stage pipeline that integrates a cutting-edge vision-language model, a detection model, a segmentation model, alongside task-specific in-painting procedures and strict postprocessing.

Alex Bores, a Democrat from New York vying for a House seat, during a'Get Out The Vote' rally on the first day of early voting for a primary election in New York City. Alex Bores, a Democrat from New York vying for a House seat, during a'Get Out The Vote' rally on the first day of early voting for a primary election in New York City. New York City House primary emerges as key battleground in'AI civil war' T he artificial intelligence industry is spending heavily in the 2026 midterms, hoping to secure influence over the technology's first generation of legislation - and New York City's primary has emerged as the key battleground. AI-focused Super Pacs have raised over $100m this cycle, of which $49m has been spent so far, in dozens of congressional races across the country. Half of all spending has converged on a single Manhattan race: Tuesday's Democratic primary in the district of NY-12.

Local modify geometry-controllable local parts of CAD models computer automatically -aided design, enhancing (CAD) design generation efficienc aims y. to It also geometric ensures instructions that the shapes (e.g., of an ne isosceles wly generated right triangle local parts or a follo rectangle w user with -specific one corner this goal.

Math reasoning has been one crucial ability of large language models (LLMs), where significant advancements have been achieved in recent years. However, most efforts focus on LLMs by curating high-quality annotation data and intricate training (or inference) paradigms, while the math reasoning performance of multimodal LLMs (MLLMs) remains lagging behind. Since the MLLM typically consists of an LLM and a vision block, we wonder: Can MLLMs directly absorb math reasoning abilities from off-the-shelf math LLMs without tuning? Recent model-merging approaches may offer insights into this question. However, they overlook the alignment between the MLLM and LLM, where we find that there is a large gap between their parameter spaces, resulting in lower performance. Our empirical evidence reveals two key factors behind this issue: the identification of crucial reasoning-associated layers in the model and the mitigation of the gaps in parameter space. Based on the empirical insights, we propose IP-Merging that first Identifies the reasoning-associated parameters in both MLLM and Math LLM, then Projects them into the subspace of MLLM, aiming to maintain the alignment, and finally merges parameters in this subspace. IP-Merging is a tuning-free approach since parameters are directly adjusted. Extensive experiments demonstrate that our IP-Merging method can enhance the math reasoning ability of MLLMs directly from Math LLMs without compromising their other capabilities.

Several recently introduced deep learning optimizers utilizing matrix-level preconditioning have shown promising speedups relative to the current dominant optimizer AdamW, particularly in relatively small-scale experiments. However, efforts to validate and replicate their successes have reported mixed results. To better understand the effectiveness of these optimizers at scale, in this work we investigate how to scale preconditioned optimizers via hyperparameter transfer, building on prior works such as µP. We study how the optimal learning rate and weight decay should scale with model width and depth for a wide range of optimizers, including Shampoo, SOAP, and Muon, accounting for the impact of commonly used techniques such as blocking and grafting. We find that scaling the learning rate according to µP improves transfer, but can still suffer from significant finite-width deviations that cause drifting optimal learning rates, which we show can be mitigated by blocking and explicit spectral normalization. For compute-optimal scaling, we find scaling independent weight decay as 1/width is nearly optimal across optimizers. Applying these scaling rules, we show Muon, SOAP and Shampoo consistently achieve near 1.4 speedup over AdamW for training Llama-architecture language models of sizes ranging from 190M to 1.4B, whereas the speedup vanishes rapidly with scale under incorrect scaling. Based on these results and further ablations, we argue that studying optimal hyperparameter transfer is essential for reliably comparing optimizers at scale given a realistic tuning budget.

Generative models trained on natural sequences are increasingly used to predict the effects of genetic variation, enabling progress in therapeutic design, disease risk prediction, and synthetic biology. In the zero-shot setting, variant impact is estimated by comparing the likelihoods of sequences, under the assumption that likelihood serves as a proxy for fitness. However, this assumption often breaks down in practice: sequence likelihood reflects not only evolutionary fitness constraints, but also phylogenetic structure and sampling biases, especially as model capacity increases. We introduce Likelihood-Fitness Bridging (LFB), a simple and general strategy that improves variant effect prediction by averaging model scores across sequences subject to similar selective pressures. Assuming an Ornstein-Uhlenbeck model of evolution, LFB can be viewed as a way to marginalize the effects of genetic drift, although its benefits appear to extend more broadly. LFB applies to existing protein and genomic language models without requiring retraining, and incurs only modest computational overhead. Evaluated on largescale deep mutational scans and clinical benchmarks, LFB consistently improves predictive performance across model families and sizes. Notably, it reverses the performance plateau observed in larger protein language models, making the largest models the most accurate when combined with LFB. These results suggest that accounting for phylogenetic and sampling biases is essential to realizing the full potential of large sequence models in variant effect prediction.

Protein language models (PLMs) are often assumed to capture evolutionary information by training on large protein sequence datasets. Yet it remains unclear whether PLMs can reason about evolution--that is, infer evolutionary relationships between sequences. We test this capability by evaluating whether standard PLM usage, frozen or fine-tuned embeddings with distance-based comparison, supports evolutionary reasoning. Existing PLMs consistently fail to recover phylogenetic structure, despite strong performance on sequence-level tasks such as masked-token and contact prediction. We present PHYLA, a hybrid state-space and transformer model that jointly processes multiple sequences and is trained using a tree-based objective across 3,000 phylogenies spanning diverse protein families.