2028 papers
This paper introduces RbtAct, a framework that leverages peer review rebuttals as implicit supervision to train large language models to generate more actionable and specific review feedback through a novel perspective-conditioned task and a new dataset called RMR-75K.
This paper introduces MUGEN, a comprehensive benchmark revealing that Large Audio-Language Models struggle with multi-audio understanding as input scaling increases, and demonstrates that combining training-free strategies like Audio-Permutational Self-Consistency with Chain-of-Thought can significantly improve performance.
Mousse is a novel optimizer that improves upon the Muon algorithm by integrating Shampoo's Kronecker-factored preconditioning to adaptively handle the heavy-tailed curvature of deep neural networks, thereby achieving faster training convergence with negligible computational overhead.
The paper introduces ActiveUltraFeedback, an efficient active learning pipeline that leverages uncertainty estimates and novel selection strategies like Double Reverse Thompson Sampling to generate high-quality preference data, enabling Large Language Models to achieve superior alignment performance with as little as one-sixth of the annotated data required by static baselines.
The paper proposes ESAinsTOD, a unified end-to-end schema-aware instruction-tuning framework that leverages full-parameter LLM fine-tuning with instruction and schema alignment mechanisms to achieve superior performance, generalization in low-resource settings, and robustness against noise across diverse task-oriented dialog benchmarks.
This paper introduces AutoViVQA, a large-scale automatically constructed dataset for Vietnamese Visual Question Answering, and evaluates transformer-based multimodal models alongside various automatic metrics to assess their performance and alignment with human judgment in the Vietnamese context.
This study demonstrates that a custom Transformer architecture outperforms both traditional machine learning models and zero-shot generative LLMs in automatically classifying cardiac risk from large-context, unstructured Dutch electronic health records, offering a robust alternative to manual administrative coding for geriatric cardiovascular risk management.
This paper introduces an open-source framework for Graph Neural Network-based Time Series Anomaly Detection to enable reproducible experimentation and critical evaluation, demonstrating that GNNs enhance both detection performance and interpretability while highlighting the need for standardized metrics and thresholding strategies.
KV-Lock is a training-free framework for DiT-based video diffusion models that dynamically adjusts background key-value locking and classifier-free guidance scales based on hallucination detection to simultaneously enhance foreground quality and maintain background consistency.
This paper introduces MM-tau-p, a novel benchmark featuring 12 metrics to holistically evaluate the robustness and efficiency of multi-modal LLM agents in dual-control settings, specifically assessing their performance with and without user persona adaptation across domains like telecom and retail.
This paper proposes a vision-language grounded framework for interpretable synthetic data generation and evaluation in remote sensing, introducing the ARAS400k dataset which demonstrates that augmenting real data with synthetic images consistently outperforms real-data-only baselines in semantic segmentation and image captioning tasks.
This paper proposes a biologically plausible, local learning framework for time-continuous neuronal networks that approximates backpropagation through time by deriving real-time error dynamics from a prospective energy function, thereby unifying and extending the Generalized Latent Equilibrium model to enable spatiotemporal credit assignment consistent with brain circuitry.
The paper introduces Routing without Forgetting (RwF), a transformer architecture that addresses Online Continual Learning by replacing iterative gradient-based specialization with dynamic, single-step associative retrieval of input-conditioned prompts via energy-based layers, thereby achieving superior performance on class-incremental benchmarks without explicit task identifiers.
This paper demonstrates that Mamba-2's state space duality can be implemented entirely using standard XLA primitives without custom kernels, achieving portable, host-synchronization-free autoregressive caching with high performance across CPU, NVIDIA GPU, and Google Cloud TPU hardware.
This paper introduces Efficient Draft Adaptation (EDA), a parameter- and data-efficient framework that restores speculative decoding performance on fine-tuned target models through a decoupled architecture, data regeneration strategy, and sample selection mechanism, achieving superior acceptance lengths with significantly reduced training costs compared to full retraining.
The paper proposes EvoPrompt, a novel framework that achieves stable, knowledge-preserving adaptation of vision-language models in few-shot scenarios by employing a modality-shared projector and an evolutionary training strategy that decouples prompt updates into directional and magnitude components to prevent catastrophic forgetting.
This paper introduces temporal-conditioned normalizing flows (tcNF), a novel autoregressive framework that enhances multivariate time series anomaly detection by effectively modeling temporal dependencies and uncertainty to identify low-probability events with improved accuracy and robustness.
EvoDriveVLA is a novel Vision-Language-Action model for autonomous driving that overcomes perception degradation and planning instability through a collaborative distillation framework combining self-anchored visual constraints and oracle-guided trajectory optimization to achieve state-of-the-art performance.
This paper introduces RoadLogic, an open-source framework that bridges declarative OpenSCENARIO specifications and executable simulations by combining Answer Set Programming, motion planning, and specification-based monitoring to automatically generate diverse, realistic, and compliant autonomous vehicle testing scenarios.
This paper introduces Variational Mixture-of-Experts Routing (VMoER), a scalable Bayesian framework that confines uncertainty quantification to the expert-selection stage of Mixture-of-Experts Transformers, achieving significant improvements in calibration, stability, and out-of-distribution detection with negligible computational overhead.