5633 papers
This paper introduces the Conservation-Congruent Encoding (CCE) framework, a unified physical theory that defines intelligence as an irreversible process of extracting work while minimizing dissipation, thereby deriving universal computational bounds and linking thermodynamic measurement, quantum decoherence, and spacetime geometry to establish substrate-neutral constraints for both natural and artificial intelligence.
This paper introduces DrivingGen, the first comprehensive benchmark for generative driving world models that addresses the lack of rigorous evaluation by combining a diverse dataset with a novel suite of metrics to assess visual realism, trajectory plausibility, temporal coherence, and controllability, thereby revealing critical trade-offs in current state-of-the-art models.
This paper presents a three-stage, physics-guided machine learning framework applied to the Frontier exascale supercomputer that identifies significant cooling inefficiencies and demonstrates how safe, counterfactual setpoint adjustments can recover up to 96% of excess energy consumption while maintaining thermal limits.
This paper introduces Batch-of-Thought (BoT), a training-free method that enhances Large Language Model reasoning by jointly processing related queries to leverage cross-instance signals, thereby improving accuracy, calibration, and computational efficiency through a multi-agent reflection architecture.
The paper introduces R^4, a self-improving agentic framework that enhances medical image analysis by decomposing workflows into routing, retrieval, reflection, and repair stages to iteratively refine both textual reports and spatial bounding boxes, achieving significant performance gains over single-pass VLM baselines without requiring gradient-based fine-tuning.
This paper audits the LAION-Aesthetics Predictor to reveal how its algorithmic gaze reinforces Western, male, and imperial biases by disproportionately filtering content and prioritizing specific cultural aesthetics, ultimately urging a shift toward pluralistic evaluation methods in AI development.
This paper introduces "Single-Shot Planning," a secure architecture for Computer Use Agents that generates a complete, trusted execution graph before observing untrusted UI states to effectively mitigate prompt injection and branch steering attacks while maintaining competitive task performance.
This paper investigates how users detect and respond to sycophantic behavior in conversational AI through a proposed DCR epistemology, revealing that while users employ various mitigation strategies, sycophancy is not universally harmful and can provide valued emotional support for vulnerable populations, suggesting a need for context-aware AI design rather than universal elimination.
This paper introduces BoxMind, a closed-loop AI system that transforms unstructured boxing footage into hierarchical tactical indicators and predictive gradients to generate expert-level strategic recommendations, which were validated during the 2024 Paris Olympics by contributing to the Chinese National Team's historic medal success.
This paper proposes the Multifaceted Scenario-Aware Hypergraph Learning (MSAHG) framework, which addresses the limitations of existing methods in handling mobility variations across distinct contexts by constructing scenario-specific disentangled sub-hypergraphs and employing a parameter-splitting mechanism to resolve inter-scenario conflicts, thereby significantly improving next POI recommendation performance.
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.