3571 papers
The paper introduces S2DiT, a novel Streaming Sandwich Diffusion Transformer that leverages efficient attention mechanisms, a budget-aware sandwich architecture, and a 2-in-1 distillation framework to achieve high-fidelity, real-time video generation on mobile devices with performance comparable to server-grade models.
This paper investigates multi-agent contract design under equal-pay constraints, providing tight polynomial-time approximation algorithms and hardness results for various reward functions while resolving open problems in unconstrained settings and quantifying the efficiency loss of fairness via a price of equality.
This paper introduces ReViP, a novel Vision-Language-Action framework that mitigates "false completion" failures caused by proprioceptive bias through vision-proprioception rebalancing and a new benchmark suite, achieving significant performance gains over existing models.
This paper introduces ScenePilot-Bench, a large-scale benchmark built on the diverse ScenePilot-4K dataset to comprehensively evaluate and advance vision-language models in autonomous driving through multi-granularity annotations and a safety-aware, four-axis assessment framework.
This paper proposes QSTar, a novel query-guided spatial-temporal-frequency interaction method enhanced by a Query Context Reasoning block, which significantly improves Audio-Visual Question Answering performance by deeply integrating question-guided clues and audio frequency characteristics with visual perception, outperforming existing multimodal approaches on multiple benchmarks.
This paper presents a dynamic framework for maintaining -edge-connectivity in undirected simple graphs under edge insertions and deletions by combining Nagamochi-Ibaraki sparse certificates with Link-Cut Trees for efficient amortized insertions and a maximum-flow-based approach for deletions, all while keeping the graph sparse with edges.
This paper introduces BioAgent Bench, a comprehensive evaluation suite and dataset for assessing AI agents in bioinformatics, which reveals that while frontier models can reliably construct multi-step pipelines, they lack robustness against perturbations and may be unsuitable for privacy-sensitive applications compared to open-weight alternatives.
This paper introduces R2M, a novel lightweight RLHF framework that mitigates reward overoptimization by leveraging real-time policy hidden states to dynamically align the reward model with the policy's evolving distribution, rather than relying solely on static semantic representations.
This paper evaluates the impact of LLM-based news sentiment analysis on stock price prediction, demonstrating that DeBERTa outperforms other models and that an ensemble approach achieves 80% accuracy, while sentiment features provide modest improvements to various time-series forecasting architectures.
Through co-design workshops with retired Chinese women, this paper demonstrates that age-sensitive interactive dance technologies and AI-generated content can lower technical barriers and transform these dancers from passive performers into empowered co-creators of their stage performances.
This paper proposes a cognitive-flexible control framework that integrates an adaptive Deep Stochastic State-Space Model with Bayesian Model Predictive Control to ensure safety guarantees and rapid performance recovery in nonstationary cyber-physical systems through online latent representation reorganization.
The paper introduces Green-VLA, a five-stage curriculum framework that combines large-scale multimodal pretraining, embodiment-specific adaptation, and reinforcement learning to enable a single generalist policy to robustly control diverse robotic systems, including the Green humanoid, with enhanced safety and long-horizon efficiency.
This paper introduces SIM-VAIL, a scalable auditing framework that reveals how consumer AI chatbots can systematically amplify mental health vulnerabilities through cumulative, context-dependent interaction loops, highlighting the need for multidimensional safety evaluations across diverse user phenotypes.
This paper introduces AgenticLab, a real-world, model-agnostic robot agent platform and benchmark that utilizes a closed-loop pipeline to evaluate state-of-the-art vision-language models in unstructured environments, revealing critical failure modes in long-horizon manipulation that static evaluations miss.
This paper demonstrates that offloading 5G LDPC decoding to GPUs on compact edge platforms significantly improves throughput and reduces latency, thereby providing the necessary compute headroom to meet strict timing constraints for ultra-reliable low-latency vehicular communications.
This paper introduces FSTab, a framework that demonstrates how LLM-generated software exhibits predictable, recurring vulnerabilities by enabling black-box attacks based on frontend features and quantifying the consistency of these flaws across different domains and model variations.
This paper introduces LMMRec, a model-agnostic framework that leverages large language models and chain-of-thought prompting to extract fine-grained user and item motivations from heterogeneous text data, effectively aligning them with interaction signals to significantly improve multimodal recommendation performance.
This study finds no significant convergence between self-reported and game-based behavioral measures of problem-solving, suggesting that these distinct modalities provide complementary rather than redundant information for personnel selection.
This paper proposes a principled conditional diffusion guidance framework based on Doob's h-transform that enforces hard constraints without modifying pretrained score networks, introducing novel off-policy learning algorithms to estimate the necessary guidance terms and providing non-asymptotic convergence guarantees for the resulting sampler.
This mixed-methods study of 107 mothers reveals that while Large Language Models serve as valuable non-judgmental resources for emotional support and reassurance regarding childcare decisions, most users still prioritize human warmth, highlighting the technology's role as a low-risk supplement rather than a replacement for human connection.