11784 papers
SaiVLA-0 introduces a neuroscience-inspired, compute-aware Vision-Language-Action framework featuring a tripartite Cerebrum-Pons-Cerebellum architecture that decouples high-level semantics from real-time control to achieve modular scalability, active foveated vision, and significant improvements in training efficiency and task success rates.
FoleyFlow introduces a novel video-to-audio generation framework that achieves superior semantic and rhythmic synchronization by aligning unimodal encoders through masked audio-visual modeling and employing a dynamic conditional flow that utilizes temporally varying video features to guide audio synthesis.
The paper introduces DARC, a retraining-free, inference-time method that mitigates the brittleness of standard preference alignment by framing response selection as a distributionally robust, risk-sensitive decision-making process to explicitly manage annotator disagreement and tail risk without compromising average quality.
This paper proposes a gradual knowledge excavation framework that enables large language models to iteratively acquire external information and perform logical reasoning, achieving state-of-the-art performance on complex open-domain question answering with significantly fewer parameters.
This paper proposes a novel explainable hybrid deep learning framework combining 1D-CNN and GRU architectures with interpretability techniques like IGs and SHAP to enhance fault detection, diagnosis, and root cause analysis in automotive software system validation while overcoming the limitations of traditional black-box models.
This paper introduces the Condition Insight Agent, a deployed decision-support framework that integrates heterogeneous industrial data sources through constrained, rule-verified LLM reasoning to generate evidence-grounded maintenance explanations and actionable advice while ensuring reliability and human oversight.
This paper introduces ESC, an Evolution Strategy-based calibration method that addresses the unique challenges of audio signal quantization by optimizing activation scaling, thereby achieving near-lossless performance for INT4 and full INT8 quantization across multiple speech tasks.
This paper demonstrates that performing reasoning in a continuous latent space via the CODI framework significantly outperforms standard explicit reasoning in multilingual settings, particularly for low-resource and zero-shot scenarios, while achieving substantial compression of reasoning traces.
This paper reveals that hidden states in end-to-end full-duplex speech models like SALM-Duplex and Moshi significantly leak speaker identity, and proposes two streaming anonymization methods using Stream-Voice-Anon that effectively mitigate this privacy risk while maintaining low-latency dialogue performance.
This paper introduces TildeOpen LLM, a 30-billion-parameter open-weight model that achieves superior performance across 34 European languages, particularly for low-resource groups, by employing curriculum learning and dataset upsampling to address data imbalances without requiring increased computational resources.
This paper proposes MM-TS, a novel framework for multi-modal contrastive learning that dynamically adjusts temperature and margin schedules based on local data distribution to address long-tail imbalances, unifying InfoNCE and max-margin objectives to achieve state-of-the-art performance across multiple image- and video-language datasets.
This paper critiques the reliance of current tabular foundation model benchmarks on point-estimate metrics like MSE, advocating instead for the adoption of proper scoring rules such as CRPS to evaluate probabilistic forecasts and the use of finetuning or promptable strategies to align model inductive biases with distributional regression goals.
This paper proposes two novel fusion strategies, Registration-aware Guided Image Fusion (RGIF) and Reliability-Gated Modality-Attention Fusion (RGMAF), which effectively integrate heterogeneous thermal and visual sensor data to significantly enhance unmanned aerial vehicle detection performance across diverse perspectives and resolutions.
This paper extends the adaptive aggregation method of AsyncFedED by exploring alternative distance metrics to better capture gradient staleness in asynchronous federated learning, demonstrating that specific metrics improve convergence, accuracy, and stability under heterogeneous and non-IID conditions.
SplitAgent introduces a novel distributed architecture that enables privacy-preserving collaboration between enterprise and cloud AI agents by utilizing context-aware dynamic sanitization, differential privacy, and zero-knowledge verification to achieve high task accuracy while significantly reducing data leakage compared to static approaches.
This paper introduces a systematic framework for Large Audio-Language Models that reformulates ambiguous emotion recognition as a distributional reasoning problem, utilizing an ambiguity-aware objective and structured chain-of-thought supervision to significantly improve performance on standard benchmarks.
This paper investigates the continuation-triggered jailbreak phenomenon in large language models, revealing through mechanistic interpretability analysis that its root cause lies in the inherent competition between the model's intrinsic continuation drive and its safety alignment defenses, while also identifying distinct behavioral patterns in safety-critical attention heads across different architectures.
This study leverages the MICCAI 2024 UWF4DR dataset to benchmark state-of-the-art deep learning models, including CNNs, Vision Transformers, and foundation models, in both spatial and frequency domains for image quality assessment, referable diabetic retinopathy detection, and diabetic macular edema identification using ultra-widefield imaging, demonstrating that feature-level fusion and frequency-domain representations yield robust and explainable results.
This paper introduces Fibration Policy Optimization (FiberPO), a unified framework that bridges trust-region theory and compositional algebraic structures to enable principled, multi-scale stability control in large language model training through the novel Aggregational Policy Censoring Objective and Fiber Bundle Gating mechanism.
The paper introduces FinToolBench, the first real-world, runnable benchmark that evaluates LLM agents on 760 executable financial tools using a novel framework assessing timeliness, intent, and regulatory compliance, alongside a proposed finance-aware baseline named FATR to advance trustworthy agentic AI in finance.