6292 papers
This paper proposes SILVR, a self-improving framework that enables visual robotic planners to iteratively enhance their performance on novel tasks by continuously updating an in-domain video model using self-collected trajectories, achieving robust results without requiring ground-truth reward functions or expert demonstrations.
The paper introduces ReLIFT, a novel training framework that interleaves reinforcement learning with online supervised fine-tuning on challenging questions, enabling large language models to acquire new knowledge and reasoning patterns beyond their original capabilities while achieving superior performance with significantly less demonstration data.
This survey provides a comprehensive overview of differential privacy in machine learning, tracing its theoretical evolution from symbolic AI to large language models, examining integration methods for privacy-preserving training, and outlining practical evaluation techniques.
This paper introduces Locality-aware Parallel Decoding (LPD), a novel framework combining flexible parallelized autoregressive modeling and locality-aware generation ordering to significantly accelerate autoregressive image generation by reducing inference steps and latency while maintaining high-quality results.
This paper argues that the interaction between human cognitive biases and AI chatbot behaviors like sycophancy creates dangerous feedback loops that can destabilize beliefs and exacerbate mental illness, necessitating coordinated interventions across clinical, technical, and regulatory domains.
This paper introduces the novel concept of Ethically Sourced Code Generation (ES-CodeGen) as a framework for managing the entire lifecycle of code generation models through ethical and sustainable practices, establishing an 11-dimension taxonomy and identifying key consequences through a comprehensive literature review and practitioner survey.
IntrinsicWeather is a diffusion-based framework that achieves controllable weather editing by decomposing images into intrinsic maps (geometry, material, and lighting) for enhanced spatial control and utilizing CLIP-space interpolation for fine-grained weather manipulation, outperforming existing methods on both synthetic and real-world datasets.
This paper reveals that the Key-Value (KV) cache used to accelerate Large Language Model inference is vulnerable to privacy attacks that allow attackers to reconstruct sensitive user inputs, and it proposes KV-Cloak, a lightweight and efficient obfuscation defense that effectively prevents such leakage without compromising model accuracy or performance.
This paper introduces the Yokai Learning Environment (YLE), a new open-source benchmark for zero-shot coordination that overcomes the saturation of the Hanabi Learning Environment by requiring agents to track moving cards and reason under ambiguous hints, thereby revealing that current state-of-the-art methods fail to maintain consistent internal models when paired with unseen partners.
This paper investigates whether next-token prediction can learn symbolic STRIPS world models for planning, finding that while a specialized STRIPS Transformer offers theoretical alignment, a standard transformer with stick-breaking attention achieves superior training accuracy and generalization, enabling effective planning across unseen states and goals.
This paper theoretically characterizes the global minimizers of sigmoid contrastive loss as -Constellations, providing a rigorous explanation for the success of SigLIP models, the origin of the modality gap, and the necessary dimensionality for high-quality representations while proposing an improved reparameterization for training dynamics.
RADAR is a lightweight, interpretable routing framework that optimizes the performance-cost tradeoff for reasoning LLMs by leveraging psychometric-inspired item response modeling to dynamically match query difficulties with appropriate model-budget pairs across diverse benchmarks.
This paper introduces a benchmark to reveal significant tool-selection bias in large language models driven by metadata alignment and pre-training exposure, and proposes a lightweight filtering-and-sampling strategy to mitigate these fairness issues while maintaining task coverage.
This paper introduces MonitorVLM, a novel vision-language framework that leverages a specialized mining dataset and innovative modules for clause filtering and behavior magnification to significantly outperform baseline models in automatically detecting safety violations from surveillance video streams in mining operations.
This paper presents the first systematic evaluation of self-supervised learning for label-efficient sleep staging using wearable EEG, demonstrating that a specialized SSL pipeline significantly outperforms supervised baselines and general-purpose foundation models by achieving clinical-grade accuracy with only 5–10% of labeled data.
The paper proposes HyWA, a novel Personalized Voice Activity Detection (PVAD) approach that utilizes a hypernetwork to generate personalized weights for selected layers of a standard VAD model, demonstrating consistent performance improvements and enhanced deployment flexibility compared to existing speaker-conditioning methods.
This paper introduces "Reveal-to-Revise," an explainable, bias-aware generative framework that unifies cross-modal attention, Grad-CAM++ attribution, and iterative feedback to achieve state-of-the-art performance and fairness in multimodal image generation and text classification tasks.
The paper introduces MVCustom, a novel diffusion-based framework that unifies multi-view camera pose control and prompt-based customization by leveraging a feature-field representation for training and employing depth-aware rendering with consistent latent completion during inference to ensure both geometric consistency and subject fidelity.
This paper introduces the Hermite eigenstructure ansatz (HEA), a theoretical framework that accurately predicts kernel regression learning curves on real datasets using only the empirical data covariance and target function decomposition, by approximating kernel eigenstructures as Hermite polynomials and demonstrating that MLPs in the feature-learning regime follow similar learning patterns.
KVTC is a lightweight, model-agnostic transform coder that achieves up to 20 (or higher) compression of Key-Value caches for large language models by combining PCA-based decorrelation, adaptive quantization, and entropy coding, thereby enabling memory-efficient serving with reusable caches while maintaining high reasoning and long-context accuracy.