2092 papers
The paper proposes B-DENSE, a novel distillation framework that leverages multi-branch trajectory alignment to enforce dense intermediate supervision, thereby overcoming the structural information loss and discretization errors of existing methods to achieve superior image generation quality with reduced inference latency.
The paper introduces "Infusion," a framework that leverages scalable influence-function approximations to compute subtle perturbations in training data, demonstrating that modifying as little as 0.2% of a dataset can effectively and transferably shape model behavior across vision and language domains.
This paper presents an automated system using LLM-powered web research agents to generate and resolve diverse, real-world forecasting questions at scale, demonstrating high-quality question creation and resolution rates that surpass human-curated platforms while effectively evaluating and improving AI forecasting performance.
This paper introduces Bayesian Generative Modeling (BGM), a unified framework that leverages a stochastic iterative Bayesian updating algorithm to learn a single generative model capable of performing arbitrary conditional inference with principled uncertainty quantification, without requiring retraining for different conditioning structures.
This paper introduces EMFusion, a conditional multivariate diffusion-based framework that leverages a residual U-Net with cross-attention and imputation-based sampling to provide accurate, uncertainty-quantified, frequency-selective electromagnetic field forecasts for wireless network planning, significantly outperforming existing baseline models.
This paper introduces ELERAG, an enhanced Retrieval-Augmented Generation system that integrates Wikidata-based Entity Linking and a hybrid re-ranking strategy to significantly improve factual accuracy in Italian educational question-answering, particularly outperforming standard methods in domain-specific contexts while demonstrating the importance of domain-adapted strategies.
This paper proposes "Periodic Asynchrony," a framework that accelerates LLM reinforcement learning by decoupling inference and training into a provably on-policy asynchronous pipeline, achieving a 3- to 5-fold throughput improvement on NPU platforms without sacrificing accuracy.
This paper introduces a novel in-context learning approach using Time-Series Foundation Models (TSFMs) to classify bearing health status from vibration data without fine-tuning, enabling scalable, zero-shot maintenance solutions across varying operational conditions.
This paper proposes LTSV, a lightweight and efficient method for valuing time series data in foundation models by leveraging in-context finetuning and temporal block aggregation to overcome the computational bottlenecks and temporal dependency limitations of traditional approaches.
This paper proposes a structured matrix scaling approach for multi-class calibration that leverages theoretical insights from logistic regression, combined with structured regularization and robust optimization, to effectively manage the bias-variance tradeoff and achieve substantial performance gains over existing methods while providing an open-source implementation.
The paper proposes GraphKeeper, a novel framework for Graph Domain-Incremental Learning that addresses catastrophic forgetting through knowledge disentanglement and deviation-free preservation, achieving state-of-the-art performance across multiple graph domains while remaining compatible with various graph foundation models.
FALCON addresses the spatial reasoning limitations of existing 2D-based vision-language-action models by leveraging spatial foundation models to inject rich 3D geometric priors directly into the action head, achieving state-of-the-art performance across diverse simulation and real-world tasks without requiring architectural changes or specialized sensors.
RL-100 is a unified real-world reinforcement learning framework that combines diffusion visuomotor policies with a clipped PPO objective and consistency distillation to achieve 100% success across 1,000 diverse robotic manipulation trials, matching or surpassing human experts while demonstrating robust zero-shot generalization and continuous deployment in dynamic environments.
This paper introduces REAP, a novel expert pruning method that outperforms existing merging techniques for compressing Mixture-of-Experts models in generative tasks by leveraging router gate-values and activation norms to minimize reconstruction error, achieving near-lossless compression even at 50% expert reduction.
The paper introduces RECODE, an agentic framework that enhances visual question answering by reverse-engineering structured visuals into executable code through iterative generation and selection, thereby transforming ambiguous perceptual tasks into verifiable symbolic reasoning problems that significantly outperform existing methods.
The Latent Speech-Text Transformer (LST) improves the efficiency and performance of auto-regressive speech-text models by aggregating speech tokens into latent patches, which aligns sequence granularity with text, reduces computational costs, and achieves significant accuracy gains across speech and text benchmarks.
This paper proposes and evaluates a novel educational approach that uses AI-generated singing and virtual avatars to transform traditional text-based syllabi into engaging audiovisual performances, demonstrating that this method significantly improves student awareness and recall of critical course information.
This paper introduces Latent Policy Steering (LPS), a method that leverages embodiment-agnostic optical flow to pretrain a World Model on diverse datasets, which is then fine-tuned with limited target-embodiment demonstrations to steer and significantly improve visuomotor policies in low-data regimes.
The paper proposes ConLID, a supervised contrastive learning approach that learns domain-invariant representations to significantly improve language identification performance for low-resource languages on out-of-domain data while maintaining accuracy for high-resource languages.
The paper introduces ChannelTokenFormer, a unified Transformer-based framework that simultaneously addresses the challenges of complex inter-channel dependencies, asynchronous sampling, and missing values to achieve robust real-world multivariate time series forecasting.