ViPO: Visual Preference Optimization at Scale

While preference optimization is crucial for improving visual generative models, how to effectively scale this paradigm remains largely unexplored. Current open-source preference datasets contain conflicting preference patterns, where winners excel in some dimensions but underperform in others. Naively optimizing on such noisy datasets fails to learn preferences, hindering effective scaling. To enhance robustness against noise, we propose Poly-DPO, which extends the DPO objective with an additional polynomial term that dynamically adjusts model confidence based on dataset characteristics, enabling effective learning across diverse data distributions. Beyond biased patterns, existing datasets suffer from low resolution, limited prompt diversity, and imbalanced distributions. To facilitate large-scale visual preference optimization by tackling data bottlenecks, we construct ViPO, a massive-scale preference dataset with 1M image pairs at 1024px across five categories and 300K video pairs at 720p+ across three categories. State-of-the-art generative models and diverse prompts ensure reliable preference signals with balanced distributions. Remarkably, when applying Poly-DPO to our high-quality dataset, the optimal configuration converges to standard DPO. This convergence validates dataset quality and Poly-DPO's adaptive nature: sophisticated optimization becomes unnecessary with sufficient data quality, yet remains valuable for imperfect datasets. We validate our approach across visual generation models. On noisy datasets like Pick-a-Pic V2, Poly-DPO achieves 6.87 and 2.32 gains over Diffusion-DPO on GenEval for SD1.5 and SDXL, respectively. For ViPO, models achieve performance far exceeding those trained on existing open-source preference datasets. These results confirm that addressing both algorithmic adaptability and data quality is essential for scaling visual preference optimization.

Learning from Noisy Preferences: A Semi-Supervised Learning Approach to Direct Preference Optimization

Human visual preferences are inherently multi-dimensional, encompassing aesthetics, detail fidelity, and semantic alignment. However, existing datasets provide only single, holistic annotations, resulting in severe label noise: images that excel in some dimensions but are deficient in others are simply marked as winner or loser. We theoretically demonstrate that compressing multi-dimensional preferences into binary labels generates conflicting gradient signals that misguide Diffusion Direct Preference Optimization (DPO). To address this, we propose Semi-DPO, a semi-supervised approach that treats consistent pairs as clean labeled data and conflicting ones as noisy unlabeled data. Our method starts by training on a consensus-filtered clean subset, then uses this model as an implicit classifier to generate pseudo-labels for the noisy set for iterative refinement. Experimental results demonstrate that Semi-DPO achieves state-of-the-art performance and significantly improves alignment with complex human preferences, without requiring additional human annotation or explicit reward models during training. We will release our code and models at: https://github.com/L-CodingSpace/semi-dpo

Projected Attainable Speed Space: A Driving Efficiency Metric Connecting Instantaneous Evaluation to Travel Time

Inefficient driving behaviors, such as overly conservative yielding, remain a key obstacle to deployment of autonomous vehicles (AVs). Instantaneous driving efficiency metrics are crucial for self-driving decision-making because they affect real-time performance evaluation and control optimization. However, commonly used indicators, including speed, relative speed, and inter-vehicle distance, are limited in capturing traffic context and in ensuring consistency between instantaneous outputs and travel-level outcomes. This study proposes the Projected Attainable Speed Space (PASS) model, a unified framework for driving efficiency assessment across instantaneous and travel-level analyses by integrating kinematic and spatial traffic information. PASS characterizes instantaneous driving efficiency with two coupled elements: potential for speed improvement (available acceleration space) and response to that potential (utilization of available acceleration space). Available acceleration space is referenced to projected attainable speed, derived from an idealized catch-up maneuver using relative speed and spacing to the leading vehicle; utilization is represented by the temporal change in available acceleration space. To ensure cross-scale consistency, time-aggregated PASS is defined as a travel-level efficiency metric. Trajectory data from a driving simulation experiment are used for parameter calibration to maximize agreement between time-aggregated PASS and observed travel times. Across 10 lane-change events, results show strong consistency, with an average coefficient of determination of 0.913, validating PASS for consistent efficiency evaluation across instantaneous and travel-level temporal scales. This study provides a unified, physically grounded framework that supports real-time decision-making and long-term performance analysis in autonomous driving.

Conditional Imputation for Within-Modality Missingness in Multi-Modal Federated Learning

Multimodal Federated Learning (MMFL) enables privacy-preserving collaborative training, but real-world clinical applications often suffer from within-modality missingness caused by sensor intermittency or irregular sampling. Existing methods implicitly represent unobserved data via architectural alignment or missing embeddings, often failing to recover the true distribution and yielding sub-optimal performance. We propose CondI, a federated framework explicitly addressing this missingness using conditional diffusion models. CondI employs a two-phase training pipeline: first, imputing unobserved temporal components using available multimodal context and conditional embeddings; second, optimizing modality-specific extractors and joint embedding spaces. During inference, imputed raw data pass through trained extractors to generate robust features, providing a holistic representation for downstream tasks. Explicit data imputation ensures models operate on complete semantic structures, significantly enhancing resilience against severe data incompleteness. Experiments on three clinical datasets (PTB-XL, SLEEP-EDF, MIMIC-IV) demonstrate CondI achieves comparable results to state-of-the-art baselines. Code: https://github.com/ZhengWugeng/CondI

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders

Reinforcement learning (RL) effectively optimizes Large Language Model (LLM)-based recommenders by contrasting positive and negative items. Empirically, training with beam-search negatives consistently outperforms random negatives, yet the mechanism is not well understood. We address this gap by analyzing the induced optimization objective and show that: (i) Under binary reward feedback, optimizing LLM recommenders with Group Relative Policy Optimization (GRPO) is theoretically equivalent to maximizing the Area Under the ROC Curve (AUC), which is often misaligned with Top-$K$ recommendation; and (ii) Replacing random negatives with beam-search negatives reshapes the objective toward partial AUC, improving alignment with Top-$K$ metrics. Motivated by this perspective, we introduce Windowed Partial AUC (WPAUC), which constrains the false positive rate (FPR) to a window [$α,α+d$] to more directly align with Top-$K$ metrics. We further propose an efficient Threshold-Adjusted Windowed reweighting (TAWin) RL method for its optimization, enabling explicit control over the targeted Top-$K$ performance. Experiments on four real-world datasets validate the theory and deliver consistent state-of-the-art performance.

FoodSense: A Multisensory Food Dataset and Benchmark for Predicting Taste, Smell, Texture, and Sound from Images

Humans routinely infer taste, smell, texture, and even sound from food images a phenomenon well studied in cognitive science. However, prior vision language research on food has focused primarily on recognition tasks such as meal identification, ingredient detection, and nutrition estimation. Image-based prediction of multisensory experience remains largely unexplored. We introduce FoodSense, a human-annotated dataset for cross-sensory inference containing 66,842 participant-image pairs across 2,987 unique food images. Each pair includes numeric ratings (1-5) and free-text descriptors for four sensory dimensions: taste, smell, texture, and sound. To enable models to both predict and explain sensory expectations, we expand short human annotations into image-grounded reasoning traces. A large language model generates visual justifications conditioned on the image, ratings, and descriptors. Using these annotations, we train FoodSense-VL, a vision language benchmark model to produce both multisensory ratings and grounded explanations directly from food images. This work connects cognitive science findings on cross-sensory perception with modern instruction tuning for multimodal models and shows that many popular evaluation metrics are insufficient for visually sensory inference.

TOPCELL: Topology Optimization of Standard Cell via LLMs

Transistor topology optimization is a critical step in standard cell design, directly dictating diffusion sharing efficiency and downstream routability. However, identifying optimal topologies remains a persistent bottleneck, as conventional exhaustive search methods become computationally intractable with increasing circuit complexity in advanced nodes. This paper introduces TOPCELL, a novel and scalable framework that reformulates high-dimensional topology exploration as a generative task using Large Language Models (LLMs). We employ Group Relative Policy Optimization (GRPO) to fine-tune the model, aligning its topology optimization strategy with logical (circuit) and spatial (layout) constraints. Experimental results within an industrial flow targeting an advanced 2nm technology node demonstrate that TOPCELL significantly outperforms foundation models in discovering routable, physically-aware topologies. When integrated into a state-of-the-art (SOTA) automation flow for a 7nm library generation task, TOPCELL exhibits robust zero-shot generalization and matches the layout quality of exhaustive solvers while achieving an 85.91x speedup.

Text-Attributed Knowledge Graph Enrichment with Large Language Models for Medical Concept Representation

In electronic health record (EHR) mining, learning high-quality representations of medical concepts (e.g., standardized diagnosis, medication, and procedure codes) is fundamental for downstream clinical prediction. However, robust concept representation learning is hindered by two key challenges: (i) clinically important cross-type dependencies (e.g., diagnosis-medication and medication-procedure relations) are often missing or incomplete in existing ontology resources, limiting the ability to model complex EHR patterns; and (ii) rich clinical semantics are often missing from structured resources, and even when available as text, are difficult to integrate with KG structure for representation learning. To address these challenges, we present CoMed, an LLM-empowered graph learning framework for medical concept representation. CoMed first builds a global knowledge graph (KG) over medical codes by combining statistically reliable associations mined from EHRs with type-constrained LLM prompting to infer semantic relations. It then utilizes LLMs to enrich the KG into a text-attributed graph by generating node descriptions and edge rationales, providing semantic signals for both concepts and their relationships. Finally, CoMed jointly trains a LoRA-tuned LLaMA text encoder with a heterogeneous GNN, fusing text semantics and graph structure into unified concept embeddings. Extensive experiments on MIMIC-III and MIMIC-IV show that CoMed consistently improves prediction performance and serves as an effective plug-in concept encoder for standard EHR pipelines.

Fall Risk and Gait Analysis in Community-Dwelling Older Adults using World-Spaced 3D Human Mesh Recovery

Gait assessment is a key clinical indicator of fall risk and overall health in older adults. However, standard clinical practice is largely limited to stopwatch-measured gait speed. We present a pipeline that leverages a 3D Human Mesh Recovery (HMR) model to extract gait parameters from recordings of older adults completing the Timed Up and Go (TUG) test. From videos recorded across different community centers, we extract and analyze spatiotemporal gait parameters, including step time, sit-to-stand duration, and step length. We found that video-derived step time was significantly correlated with IMU-based insole measurements. Using linear mixed effects models, we confirmed that shorter, more variable step lengths and longer sit-to-stand durations were predicted by higher self-rated fall risk and fear of falling. These findings demonstrate that our pipeline can enable accessible and ecologically valid gait analysis in community settings.

LiveGesture Streamable Co-Speech Gesture Generation Model

We propose LiveGesture, the first fully streamable, speech-driven full-body gesture generation framework that operates with zero look-ahead and supports arbitrary sequence length. Unlike existing co-speech gesture methods, which are designed for offline generation and either treat body regions independently or entangle all joints within a single model, LiveGesture is built from the ground up for causal, region-coordinated motion generation. LiveGesture consists of two main modules: the Streamable Vector Quantized Motion Tokenizer (SVQ) and the Hierarchical Autoregressive Transformer (HAR). The SVQ tokenizer converts the motion sequence of each body region into causal, discrete motion tokens, enabling real-time, streamable token decoding. On top of SVQ, HAR employs region-expert autoregressive (xAR) transformers to model expressive, fine-grained motion dynamics for each body region. A causal spatio-temporal fusion module (xAR Fusion) then captures and integrates correlated motion dynamics across regions. Both xAR and xAR Fusion are conditioned on live, continuously arriving audio signals encoded by a streamable causal audio encoder. To enhance robustness under streaming noise and prediction errors, we introduce autoregressive masking training, which leverages uncertainty-guided token masking and random region masking to expose the model to imperfect, partially erroneous histories during training. Experiments on the BEAT2 dataset demonstrate that LiveGesture produces coherent, diverse, and beat-synchronous full-body gestures in real time, matching or surpassing state-of-the-art offline methods under true zero look-ahead conditions.