Generating animated 3D objects is at the heart of many applications, yet most advanced works are typically difficult to apply in practice because of their limited setup, their long runtime, or their limited quality. We introduce ActionMesh, a generative model that predicts production-ready 3D meshes "in action" in a feed-forward manner. Drawing inspiration from early video models, our key insight is to modify existing 3D diffusion models to include a temporal axis, resulting in a framework we dubbed "temporal 3D diffusion". Specifically, we first adapt the 3D diffusion stage to generate a sequence of synchronized latents representing time-varying and independent 3D shapes. Second, we design a temporal 3D autoencoder that translates a sequence of independent shapes into the corresponding deformations of a pre-defined reference shape, allowing us to build an animation. Combining these two components, ActionMesh generates animated 3D meshes from different inputs like a monocular video, a text description, or even a 3D mesh with a text prompt describing its animation. Besides, compared to previous approaches, our method is fast and produces results that are rig-free and topology consistent, hence enabling rapid iteration and seamless applications like texturing and retargeting. We evaluate our model on standard video-to-4D benchmarks (Consistent4D, Objaverse) and report state-of-the-art performances on both geometric accuracy and temporal consistency, demonstrating that our model can deliver animated 3D meshes with unprecedented speed and quality.

Policy gradient methods are known to be highly sensitive to the choice of policy parameterization. In particular, the widely used softmax parameterization can induce ill-conditioned optimization landscapes and lead to exponentially slow convergence. Although this can be mitigated by preconditioning, this solution is often computationally expensive. Instead, we propose replacing the softmax with an alternative family of policy parameterizations based on the generalized f-softargmax. We further advocate coupling this parameterization with a regularizer induced by the same f-divergence, which improves the optimization landscape and ensures that the resulting regularized objective satisfies a Polyak-Lojasiewicz inequality. Leveraging this structure, we establish the first explicit non-asymptotic last-iterate convergence guarantees for stochastic policy gradient methods for finite MDPs without any form of preconditioning. We also derive sample-complexity bounds for the unregularized problem and show that f-PG, with Tsallis divergences achieves polynomial sample complexity in contrast to the exponential complexity incurred by the standard softmax parameterization.

Parkinson's disease (PD) and Alzheimer's disease (AD) are the two most prevalent and incurable neurodegenerative diseases (NDs) worldwide, for which early diagnosis is critical to delay their progression. However, the high dimensionality of multi-metric data with diverse structural forms, the heterogeneity of neuroimaging and phenotypic data, and class imbalance collectively pose significant challenges to early ND diagnosis. To address these challenges, we propose a dynamically weighted dual graph attention network (DW-DGAT) that integrates: (1) a general-purpose data fusion strategy to merge three structural forms of multi-metric data; (2) a dual graph attention architecture based on brain regions and inter-sample relationships to extract both micro- and macro-level features; and (3) a class weight generation mechanism combined with two stable and effective loss functions to mitigate class imbalance. Rigorous experiments, based on the Parkinson Progression Marker Initiative (PPMI) and Alzheimer's Disease Neuroimaging Initiative (ADNI) studies, demonstrate the state-of-the-art performance of our approach.

Scientific surveys require not only summarizing large bodies of literature, but also organizing them into clear and coherent conceptual structures. However, existing automatic survey generation methods typically focus on linear text generation and struggle to explicitly model hierarchical relations among research topics and structured methodological comparisons, resulting in substantial gaps in structural organization and evidence presentation compared to expert-written surveys. To address this limitation, we propose MVSS, a multi-view structured survey generation framework that jointly generates and aligns citation-grounded hierarchical trees, structured comparison tables, and survey text. MVSS follows a structure-first paradigm: it first constructs a tree that captures the conceptual organization of a research domain, then generates comparison tables constrained by the tree structure, and finally uses both the tree and tables as joint structural constraints to guide outline construction and survey text generation. This design enables complementary and aligned multi-view representations across structure, comparison, and narrative. In addition, we introduce a dedicated evaluation framework that systematically assesses generated surveys from multiple dimensions, including structural quality, comparative completeness, and citation fidelity. Through large-scale experiments on 76 computer science topics, we demonstrate that MVSS significantly outperforms existing methods in survey organization and evidence grounding, and achieves performance comparable to expert-written surveys across multiple evaluation metrics.

Reliable zero-shot detection of out-of-distribution (OOD) inputs is critical for deploying vision-language models in open-world settings. However, the lack of labeled negatives in zero-shot OOD detection necessitates proxy signals that remain effective under distribution shift. Existing negative-label methods rely on a fixed set of textual proxies, which (i) sparsely sample the semantic space beyond in-distribution (ID) classes and (ii) remain static while only visual features drift, leading to cross-modal misalignment and unstable predictions. In this paper, we propose CoEvo, a training- and annotation-free test-time framework that performs bidirectional, sample-conditioned adaptation of both textual and visual proxies. Specifically, CoEvo introduces a proxy-aligned co-evolution mechanism to maintain two evolving proxy caches, which dynamically mines contextual textual negatives guided by test images and iteratively refines visual proxies, progressively realigning cross-modal similarities and enlarging local OOD margins. Finally, we dynamically re-weight the contributions of dual-modal proxies to obtain a calibrated OOD score that is robust to distribution shift. Extensive experiments on standard benchmarks demonstrate that CoEvo achieves state-of-the-art performance, improving AUROC by 1.33% and reducing FPR95 by 45.98% on ImageNet-1K compared to strong negative-label baselines.

Medical contrastive vision-language pre-training (VLP) has demonstrated significant potential in improving performance on downstream tasks. Traditional approaches typically employ contrastive learning, treating paired image-report samples as positives and unpaired ones as negatives. However, in medical datasets, there can be substantial similarities between images or reports from different patients. Rigidly treating all unpaired samples as negatives, can disrupt the underlying semantic structure and negatively impact the quality of the learned representations. In this paper, we propose a multi-level alignment framework, Representation Learning with Semantic-aware Instance and Sparse Token Alignments (SISTA) by exploiting the semantic correspondence between medical image and radiology reports at two levels, i.e., image-report and patch-word levels. Specifically, we improve the conventional contrastive learning by incorporating inter-report similarity to eliminate the false negatives and introduce a method to effectively align image patches with relevant word tokens. Experimental results demonstrate the effectiveness of the proposed framework in improving transfer performance across different datasets on three downstream tasks: image classification, image segmentation, and object detection. Notably, our framework achieves significant improvements in fine-grained tasks even with limited labeled data. Codes and pre-trained models will be made available.

Reasoning Large Language Models (RLLMs) excelling in complex tasks present unique challenges for digital watermarking, as existing methods often disrupt logical coherence or incur high computational costs. Token-based watermarking techniques can corrupt the reasoning flow by applying pseudo-random biases, while semantic-aware approaches improve quality but introduce significant latency or require auxiliary models. This paper introduces ReasonMark, a novel watermarking framework specifically designed for reasoning-intensive LLMs. Our approach decouples generation into an undisturbed Thinking Phase and a watermarked Answering Phase. We propose a Criticality Score to identify semantically pivotal tokens from the reasoning trace, which are distilled into a Principal Semantic Vector (PSV). The PSV then guides a semantically-adaptive mechanism that modulates watermark strength based on token-PSV alignment, ensuring robustness without compromising logical integrity. Extensive experiments show ReasonMark surpasses state-of-the-art methods by reducing text Perplexity by 0.35, increasing translation BLEU score by 0.164, and raising mathematical accuracy by 0.67 points. These advancements are achieved alongside a 0.34% higher watermark detection AUC and stronger robustness to attacks, all with a negligible increase in latency. This work enables the traceable and trustworthy deployment of reasoning LLMs in real-world applications.

Developing foundation models in medical imaging requires continuous monitoring of downstream performance. Researchers are burdened with tracking numerous experiments, design choices, and their effects on performance, often relying on ad-hoc, manual workflows that are inherently slow and error-prone. We introduce EvalBlocks, a modular, plug-and-play framework for efficient evaluation of foundation models during development. Built on Snakemake, EvalBlocks supports seamless integration of new datasets, foundation models, aggregation methods, and evaluation strategies. All experiments and results are tracked centrally and are reproducible with a single command, while efficient caching and parallel execution enable scalable use on shared compute infrastructure. Demonstrated on five state-of-the-art foundation models and three medical imaging classification tasks, EvalBlocks streamlines model evaluation, enabling researchers to iterate faster and focus on model innovation rather than evaluation logistics. The framework is released as open source software at https://github.com/DIAGNijmegen/eval-blocks.

Recent advances in text-to-image diffusion models have demonstrated remarkable generation capabilities, yet they raise significant concerns regarding safety, copyright, and ethical implications. Existing concept erasure methods address these risks by removing sensitive concepts from pre-trained models, but most of them rely on data-intensive and computationally expensive fine-tuning, which poses a critical limitation. To overcome these challenges, inspired by the observation that the model's activations are predominantly composed of generic concepts, with only a minimal component can represent the target concept, we propose a novel training-free method (ActErase) for efficient concept erasure. Specifically, the proposed method operates by identifying activation difference regions via prompt-pair analysis, extracting target activations and dynamically replacing input activations during forward passes. Comprehensive evaluations across three critical erasure tasks (nudity, artistic style, and object removal) demonstrates that our training-free method achieves state-of-the-art (SOTA) erasure performance, while effectively preserving the model's overall generative capability. Our approach also exhibits strong robustness against adversarial attacks, establishing a new plug-and-play paradigm for lightweight yet effective concept manipulation in diffusion models.

Efficient target localization and autonomous navigation in complex environments are fundamental to real-world embodied applications. While recent advances in multimodal foundation models have enabled zero-shot object goal navigation, allowing robots to search for arbitrary objects without fine-tuning, existing methods face two key limitations: (1) heavy reliance on ground-truth depth and pose information, which restricts applicability in real-world scenarios; and (2) lack of visual in-context learning (VICL) capability to extract geometric and semantic priors from environmental context, as in a short traversal video. To address these challenges, we propose RANGER, a novel zero-shot, open-vocabulary semantic navigation framework that operates using only a monocular camera. Leveraging powerful 3D foundation models, RANGER eliminates the dependency on depth and pose while exhibiting strong VICL capability. By simply observing a short video of the target environment, the system can also significantly improve task efficiency without requiring architectural modifications or task-specific retraining. The framework integrates several key components: keyframe-based 3D reconstruction, semantic point cloud generation, vision-language model (VLM)-driven exploration value estimation, high-level adaptive waypoint selection, and low-level action execution. Experiments on the HM3D benchmark and real-world environments demonstrate that RANGER achieves competitive performance in terms of navigation success rate and exploration efficiency, while showing superior VICL adaptability, with no previous 3D mapping of the environment required.

Self-supervised real-world image denoising remains a fundamental challenge, arising from the antagonistic trade-off between decorrelating spatially structured noise and preserving high-frequency details. Existing blind-spot network (BSN) methods rely on pixel-shuffle downsampling (PD) to decorrelate noise, but aggressive downsampling fragments fine structures, while milder downsampling fails to remove correlated noise. To address this, we introduce Next-Scale Prediction (NSP), a novel self-supervised paradigm that decouples noise decorrelation from detail preservation. NSP constructs cross-scale training pairs, where BSN takes low-resolution, fully decorrelated sub-images as input to predict high-resolution targets that retain fine details. As a by-product, NSP naturally supports super-resolution of noisy images without retraining or modification. Extensive experiments demonstrate that NSP achieves state-of-the-art self-supervised denoising performance on real-world benchmarks, significantly alleviating the long-standing conflict between noise decorrelation and detail preservation. The code is available at https://github.com/XLearning-SCU/2026-CVPR-NSP.

Deep representations across modalities are inherently intertwined. In this paper, we systematically analyze the spectral characteristics of various semantic and pixel encoders. Interestingly, our study uncovers a highly inspiring and rarely explored correspondence between an encoder's feature spectrum and its functional role: semantic encoders primarily capture low-frequency components that encode abstract meaning, whereas pixel encoders additionally retain high-frequency information that conveys fine-grained detail. This heuristic finding offers a unifying perspective that ties encoder behavior to its underlying spectral structure. We define it as the Prism Hypothesis, where each data modality can be viewed as a projection of the natural world onto a shared feature spectrum, just like the prism. Building on this insight, we propose Unified Autoencoding (UAE), a model that harmonizes semantic structure and pixel details via an innovative frequency-band modulator, enabling their seamless coexistence. Extensive experiments demonstrate that UAE effectively unifies semantic abstraction and pixel-level fidelity within a single latent space, achieving state-of-the-art performance. Moreover, we show that UAE can be directly applied to pixel-space modeling, significantly improving both FID and IS over the vanilla JIT baseline. Our code is avaliable at: https://github.com/WeichenFan/UAE.

Event cameras offer a high temporal resolution over traditional frame-based cameras, which makes them suitable for motion and structure estimation. However, it has been unclear how event-based 3D Gaussian Splatting (3DGS) approaches could leverage fine-grained temporal information of sparse events. This work proposes GPERT, a framework to address the trade-off between accuracy and temporal resolution in event-based 3DGS. Our key idea is to decouple the rendering into two branches: event-by-event geometry (depth) rendering and snapshot-based radiance (intensity) rendering, by using ray-tracing and the image of warped events. The extensive evaluation shows that our method achieves state-of-the-art performance on the real-world datasets and competitive performance on the synthetic dataset. Also, the proposed method works without prior information (e.g., pretrained image reconstruction models) or COLMAP-based initialization, is more flexible in the event selection number, and achieves sharp reconstruction on scene edges with fast training time. We hope that this work deepens our understanding of the sparse nature of events for 3D reconstruction. https://github.com/e3ai/gpert

Recent releases such as o3 highlight human-like "thinking with images" reasoning that combines tool use with stepwise verification, yet most open-source approaches still rely on text-only chains, rigid visual schemas, or single-step pipelines, limiting flexibility, interpretability, and transferability on complex tasks. We introduce CodeDance, which explores executable code as a general solver for visual reasoning. Unlike fixed-schema calls (e.g., only predicting bounding-box coordinates), CodeDance defines, composes, and executes code to orchestrate multiple tools, compute intermediate results, and render visual artifacts (e.g., boxes, lines, plots) that support transparent, self-checkable reasoning. To guide this process, we introduce a reward for balanced and adaptive tool calling, which balances exploration with efficiency and mitigates tool overuse. Interestingly, beyond the expected capabilities taught by atomic supervision, we empirically observe novel emergent behaviors during RL training: CodeDance demonstrates novel tool invocations, unseen compositions, and cross-task transfer. These behaviors arise without task-specific fine-tuning, suggesting a general and scalable mechanism for executable visual reasoning. Extensive experiments across reasoning benchmarks (e.g., visual search, math, chart QA) show that CodeDance not only consistently outperforms schema-driven and text-only baselines, but also surpasses closed models such as GPT-4o and larger open-source models.

The advent of high-quality video generation models has amplified the need for robust watermarking schemes that can be used to reliably detect and track the provenance of generated videos. Existing video watermarking methods based on both post-hoc and in-generation approaches fail to simultaneously achieve imperceptibility, robustness, and computational efficiency. This work introduces a novel framework for in-generation video watermarking called SPDMark (pronounced `SpeedMark') based on selective parameter displacement of a video diffusion model. Watermarks are embedded into the generated videos by modifying a subset of parameters in the generative model. To make the problem tractable, the displacement is modeled as an additive composition of layer-wise basis shifts, where the final composition is indexed by the watermarking key. For parameter efficiency, this work specifically leverages low-rank adaptation (LoRA) to implement the basis shifts. During the training phase, the basis shifts and the watermark extractor are jointly learned by minimizing a combination of message recovery, perceptual similarity, and temporal consistency losses. To detect and localize temporal modifications in the watermarked videos, we use a cryptographic hashing function to derive frame-specific watermark messages from the given base watermarking key. During watermark extraction, maximum bipartite matching is applied to recover the correct frame order, even from temporally tampered videos. Evaluations on both text-to-video and image-to-video generation models demonstrate the ability of SPDMark to generate imperceptible watermarks that can be recovered with high accuracy and also establish its robustness against a variety of common video modifications.

Vision-language-action (VLA) models and LLM agents have advanced rapidly, yet reliable deployment on physical robots is often hindered by an interface mismatch between agent tool APIs and robot middleware. Current implementations typically rely on ad-hoc wrappers that are difficult to reuse, and changes to the VLA backend or serving stack often necessitate extensive re-integration. We introduce RoboNeuron, a middleware layer that connects the Model Context Protocol (MCP) for LLM agents with robot middleware such as ROS2. RoboNeuron bridges these ecosystems by deriving agent-callable tools directly from ROS schemas, providing a unified execution abstraction that supports both direct commands and modular composition, and localizing backend, runtime, and acceleration-preset changes within a stable inference boundary. We evaluate RoboNeuron in simulation and on hardware through multi-platform base control, arm motion, and VLA-based grasping tasks, demonstrating that it enables modular system orchestration under a unified interface while supporting backend transitions without system rewiring. The full code implementation of this work is available at github repo: https://github.com/guanweifan/RoboNeuron

Large Language Models and multi-agent systems have shown promise in decomposing complex tasks, yet they struggle with long-horizon reasoning tasks and escalating computation cost. This work introduces a hierarchical multi-agent architecture that distributes reasoning across a 64*64 grid of lightweight agents, supported by a selective oracle. A spatial curriculum progressively expands the operational region of the grid, ensuring that agents master easier central tasks before tackling harder peripheral ones. To improve reliability, the system integrates Negative Log-Likelihood as a measure of confidence, allowing the curriculum to prioritize regions where agents are both accurate and well calibrated. A Thompson Sampling curriculum manager adaptively chooses training zones based on competence and NLL-driven reward signals. We evaluate the approach on a spatially grounded Tower of Hanoi benchmark, which mirrors the long-horizon structure of many robotic manipulation and planning tasks. Results demonstrate improved stability, reduced oracle usage, and stronger long-range reasoning from distributed agent cooperation.

Deep learning-based image restoration has achieved significant success. However, when addressing real-world degradations, model performance is limited by the quality of groundtruth images in datasets due to practical constraints in data acquisition. To address this limitation, we propose a novel framework that enhances existing ground truth images to provide higher-quality supervision for real-world restoration. Our framework generates perceptually enhanced ground truth images using super-resolution by incorporating adaptive frequency masks, which are learned by a conditional frequency mask generator. These masks guide the optimal fusion of frequency components from the original ground truth and its super-resolved variants, yielding enhanced ground truth images. This frequency-domain mixup preserves the semantic consistency of the original content while selectively enriching perceptual details, preventing hallucinated artifacts that could compromise fidelity. The enhanced ground truth images are used to train a lightweight output refinement network that can be seamlessly integrated with existing restoration models. Extensive experiments demonstrate that our approach improves the quality of restored images. We further validate the effectiveness of both supervision enhancement and output refinement through user studies.

This study investigates the impact of the invariance of feature vectors for partial-to-partial point set registration under translation and rotation of input point sets, particularly in the realm of techniques based on deep learning and Gaussian mixture models (GMMs). We reveal both theoretical and practical problems associated with such deep-learning-based registration methods using GMMs, with a particular focus on the limitations of DeepGMR, a pioneering study in this line, to the partial-to-partial point set registration. Our primary goal is to uncover the causes behind such methods and propose a comprehensible solution for that. To address this, we introduce an attention-based reference point shifting (ARPS) layer, which robustly identifies a common reference point of two partial point sets, thereby acquiring transformation-invariant features. The ARPS layer employs a well-studied attention module to find a common reference point rather than the overlap region. Owing to this, it significantly enhances the performance of DeepGMR and its recent variant, UGMMReg. Furthermore, these extension models outperform even prior deep learning methods using attention blocks and Transformer to extract the overlap region or common reference points. We believe these findings provide deeper insights into registration methods using deep learning and GMMs.

Automatic 3D reconstruction of indoor spaces from 2D floor plans necessitates high-precision semantic segmentation of structural elements, particularly walls. However, existing methods often struggle with detecting thin structures and maintaining geometric precision. To address this, we introduce MitUNet, a hybrid neural network designed to bridge the gap between global semantic context and fine-grained structural details. Our architecture combines a Mix-Transformer encoder with a U-Net decoder enhanced with spatial and channel attention blocks. Optimized with the Tversky loss function, this approach achieves a balance between precision and recall, ensuring accurate boundary recovery. Experiments on the CubiCasa5k dataset and the regional dataset demonstrate MitUNet's superiority in generating structurally correct masks with high boundary accuracy, outperforming standard models. This tool provides a robust foundation for automated 3D reconstruction pipelines. To ensure reproducibility and facilitate future research, the source code and the regional dataset are publicly available at https://github.com/aliasstudio/mitunet and https://doi.org/10.5281/zenodo.17871079, respectively.

Coordinating emergency responses in extreme environments, such as wildfires, requires resilient and high-bandwidth communication backbones. While autonomous aerial swarms can establish ad-hoc networks to provide this connectivity, the high risk of individual node attrition in these settings often leads to network fragmentation and mission-critical downtime. To overcome this challenge, we introduce and formalize the problem of Robust Task Networking Under Attrition (RTNUA), which extends connectivity maintenance in multi-robot systems to explicitly address proactive redundancy and attrition recovery. We then introduce Physics-Informed Robust Employment of Multi-Agent Networks ($Φ$IREMAN), a topological algorithm leveraging physics-inspired potential fields to solve this problem. In our evaluations, $Φ$IREMAN consistently outperforms baselines, and is able to maintain greater than $99.9\%$ task uptime despite substantial attrition in simulations with up to 100 tasks and 500 drones, demonstrating both effectiveness and scalability.

Diffusion models for continuous state spaces based on Gaussian noising processes are now relatively well understood from both practical and theoretical perspectives. In contrast, results for diffusion models on discrete state spaces remain far less explored and pose significant challenges, particularly due to their combinatorial structure and their more recent introduction in generative modelling. In this work, we establish new and sharp convergence guarantees for three popular discrete diffusion models (DDMs). Two of these models are designed for finite state spaces and are based respectively on the random walk and the masking process. The third DDM we consider is defined on the countably infinite space $\mathbb{N}^d$ and uses a drifted random walk as its forward process. For each of these models, the backward process can be characterized by a discrete score function that can, in principle, be estimated. However, even with perfect access to these scores, simulating the exact backward process is infeasible, and one must rely on time discretization. In this work, we study Euler-type approximations and establish convergence bounds in both Kullback-Leibler divergence and total variation distance for the resulting models, under minimal assumptions on the data distribution. To the best of our knowledge, this study provides the optimal non-asymptotic convergence guarantees for these noising processes that do not rely on boundedness assumptions on the estimated score. In particular, the computational complexity of each method scales only linearly in the dimension, up to logarithmic factors.

There has been significant progress in open-source text-only translation large language models (LLMs) with better language coverage and quality. However, these models can be only used in cascaded pipelines for speech translation (ST), performing automatic speech recognition first followed by translation. This introduces additional latency, which is particularly critical in simultaneous ST (SimulST), and prevents the model from exploiting multimodal context, such as images, which can aid disambiguation. Pretrained multimodal foundation models (MMFMs) already possess strong perception and reasoning capabilities across multiple modalities, but generally lack the multilingual coverage and specialized translation performance of dedicated translation LLMs. To build an effective multimodal translation system, we propose an end-to-end approach that fuses MMFMs with translation LLMs. We introduce a novel fusion strategy that connects hidden states from multiple layers of a pretrained MMFM to a translation LLM, enabling joint end-to-end training. The resulting model, OmniFusion, built on Omni 2.5-7B as the MMFM and SeedX PPO-7B as the translation LLM, can perform speech-to-text, speech-and-image-to-text, and text-and-image-to-text translation. Experiments demonstrate that OmniFusion effectively leverages both audio and visual inputs, achieves a 1-second latency reduction in SimulST compared to cascaded pipelines and also improves the overall translation quality\footnote{Code is available at https://github.com/saikoneru/OmniFusion}.

Recent advances in foundation models have shown great promise in domains such as natural language processing and computer vision, and similar efforts are now emerging in the Earth Observation community. These models aim to generalize across tasks with limited supervision, reducing the need for training separate models for each task. However, current strategies, which largely focus on scaling model size and dataset volume, require prohibitive computational and data resources, limiting accessibility to only a few large institutions. Moreover, this paradigm of ever-larger models stands in stark contrast with the principles of sustainable and environmentally responsible AI, as it leads to immense carbon footprints and resource inefficiency. In this work, we present a novel and efficient alternative: an Ensemble-of-Specialists framework for building Remote Sensing Foundation Models (RSFMs). Our method decomposes the training process into lightweight, task-specific ConvNeXtV2 specialists that can be frozen and reused. This modular approach offers strong advantages in efficiency, interpretability, and extensibility. Moreover, it naturally supports federated training, pruning, and continuous specialist integration, making it particularly well-suited for collaborative and resource-constrained settings. Our framework sets a new direction for building scalable and efficient RSFMs. All codes and pretrained models are available on the public repo at https://github.com/pierreadorni/EoS-FM .

As language models (LMs) are increasingly adopted across domains, high-quality benchmarking frameworks are essential for guiding deployment decisions. In practice, however, frameworks such as Holistic Evaluation of Language Models (HELM) typically evaluate models under a single static prompt configuration, even though model behavior depends strongly on prompt choice. As a result, reported scores can reflect prompt choice as much as model capability. Declarative prompting frameworks such as DSPy offer a scalable way to evaluate models under a set of structured prompting strategies rather than a static prompt configuration. We present a reproducible DSPy+HELM framework for studying how prompt choice impacts reported benchmark outcomes. Using five prompting methods, we evaluate four frontier and two open-source LMs across seven benchmarks against existing HELM baseline scores. By evaluating LMs across a family of prompt configurations, we find that prompt choice can materially impact leaderboard outcomes. In particular, structured prompting improves performance (by 6% on average), alters comparisons (leaderboard rankings shift on 5/7 benchmarks), with most gains coming from introducing chain-of-thought, and little additional benefit from more advanced optimizers. To our knowledge, this is the first study to systematically integrate structured prompting into an established evaluation framework and quantify how prompt choice alone can impact benchmark conclusions. We open-source (i) DSPy+HELM Evaluation (https://github.com/stanford-crfm/helm/pull/3893) and (ii) Prompt Optimization Pipeline (https://github.com/StanfordMIMI/dspy-helm).

Audio tokenization bridges continuous waveforms and multi-track music language models. In dual-track modeling, tokens should preserve three properties at once: high-fidelity reconstruction, strong predictability under a language model, and cross-track correspondence. We introduce DuoTok, a source-aware dual-track tokenizer that addresses this trade-off through staged disentanglement. DuoTok first pretrains a semantic encoder, then regularizes it with multi-task supervision, freezes the encoder, and applies hard dual-codebook routing while keeping auxiliary objectives on quantized codes. A diffusion decoder reconstructs high-frequency details, allowing tokens to focus on structured information for sequence modeling. On standard benchmarks, DuoTok achieves a favorable predictability-fidelity trade-off, reaching the lowest cnBPT while maintaining competitive reconstruction at 0.75 kbps. Under a held-constant dual-track language modeling protocol, enBPT also improves, indicating gains beyond codebook size effects. Controlled diagnostics show larger predictability costs under cross-track corruption and larger gains from longer context, suggesting that models trained on DuoTok tokens use cross-track structure and non-local history.

Quality assessment of AI-generated content is crucial for evaluating model capability and guiding model optimization. However, most existing quality assessment datasets and models provide only a single quality score, which is too coarse to offer targeted guidance for improving generative models. In current applications of AI-generated images, realism and plausibility are two critical dimensions, and with the emergence of unified generation-understanding models, fine-grained evaluation along these dimensions becomes especially effective for improving generative performance. Therefore, we introduce Q-Real, a novel dataset for fine-grained evaluation of realism and plausibility in AI-generated images. Q-Real consists of 3,088 images generated by popular text-to-image models. For each image, we annotate the locations of major entities and provide a set of judgment questions and attribution descriptions for these along the dimensions of realism and plausibility. Considering that recent advances in multi-modal large language models (MLLMs) enable fine-grained evaluation of AI-generated images, we construct Q-Real Bench to evaluate them on two tasks: judgment and grounding with reasoning. Finally, to enhance MLLM capabilities, we design a fine-tuning framework and conduct experiments on multiple MLLMs using our dataset. Experimental results demonstrate the high quality and significance of our dataset and the comprehensiveness of the benchmark. Dataset and code will be released upon publication.

Data-Free Quantization (DFQ) offers a practical solution for model compression without requiring access to real data, making it particularly attractive in privacy-sensitive scenarios. While DFQ has shown promise for unimodal models, its extension to Vision-Language Models such as Contrastive Language-Image Pre-training (CLIP) models remains underexplored. In this work, we reveal that directly applying existing DFQ techniques to CLIP results in substantial performance degradation due to two key limitations: insufficient semantic content and low intra-image diversity in synthesized samples. To tackle these challenges, we propose D4C, the first DFQ framework tailored for CLIP. D4C synthesizes semantically rich and structurally diverse pseudo images through three key components: 1) Prompt-Guided Semantic Injection aligns generated images with real-world semantics using text prompts; 2) Structural Contrastive Generation reproduces compositional structures of natural images by leveraging foreground-background contrastive synthesis; and 3) Perturbation-Aware Enhancement applies controlled perturbations to improve sample diversity and robustness. These components jointly empower D4C to synthesize images that are both semantically informative and structurally diverse, effectively bridging the performance gap of DFQ on CLIP. Extensive experiments validate the effectiveness of D4C, showing significant performance improvements on various bit-widths and models.

Accurate segmentation of myocardial scar from late gadolinium enhanced (LGE) cardiac MRI is essential for evaluating tissue viability, yet remains challenging due to variable contrast and imaging artifacts. Electrocardiogram (ECG) signals provide complementary physiological information, as conduction abnormalities can help localize or suggest scarred myocardial regions. In this work, we propose a novel multimodal framework that integrates ECG-derived electrophysiological information with anatomical priors from the AHA-17 atlas for physiologically consistent LGE-based scar segmentation. As ECGs and LGE-MRIs are not acquired simultaneously, we introduce a Temporal Aware Feature Fusion (TAFF) mechanism that dynamically weights and fuses features based on their acquisition time difference. Our method was evaluated on a clinical dataset and achieved substantial gains over the state-of-the-art image-only baseline (nnU-Net), increasing the average Dice score for scars from 0.6149 to 0.8463 and achieving high performance in both precision (0.9115) and sensitivity (0.9043). These results show that integrating physiological and anatomical knowledge allows the model to "see beyond the image", setting a new direction for robust and physiologically grounded cardiac scar segmentation.

Knowing the reliability of a model's response is essential in practical applications. Given the strong generation capabilities of large language models (LLMs), research has focused on generating verbalized confidence. This approach is further enhanced by integrating chain-of-thought reasoning, which provides logical and transparent estimates. However, how reasoning strategies affect the estimated confidence remains under-explored. In this work, we demonstrate that predicting a verbalized probability distribution effectively promotes reasoning for confidence estimation. It requires an LLM to consider all possible answers rather than relying on a single guess, and the requirement of producing a distribution elicits more careful confidence assignment. We conduct systematic experiments comparing different verbalization-based methods across multiple LLMs and tasks. Our method consistently shows advantages, whether in the simple prompting setup or after optimization via reinforcement learning (RL). Notably, it achieves higher reasoning efficacy during inference-time scaling, saving nearly 6$\times$ the computation to reach the best Brier score of the strongest baseline on MMLU-Pro. Additionally, we reveal its limitations on specific tasks and discuss possible solutions for broader applicability.