11366 papers
This paper introduces MMTU, a large-scale benchmark comprising over 28,000 questions across 25 real-world expert-level table tasks, designed to comprehensively evaluate and reveal the significant limitations of current frontier models in understanding, reasoning, and manipulating structured tabular data.
BemaGANv2 is an advanced GAN-based vocoder that enhances long-term audio generation for Text-to-Music and Text-to-Audio applications by integrating Anti-aliased Multi-Periodicity composition modules in the generator and systematically evaluating novel discriminator combination strategies, including the Multi-Envelope Discriminator, to achieve high-fidelity and temporally coherent results.
This paper introduces Co-LoRA, a collaborative personalization framework that addresses both data and model heterogeneity through a task-relevance-aware aggregation strategy and a dimension-invariant module, validated by a new multi-modal benchmark and superior performance over state-of-the-art methods.
The paper introduces ContextMatters, a framework that combines Large Language Models with classical planning to dynamically relax goals based on environmental context, significantly improving 3D scene planning success rates and enabling successful real-world robot deployment.
This paper proposes a semi-self-supervised learning approach featuring a novel GLMask representation and a semantic-to-instance pipeline that achieves state-of-the-art instance segmentation performance with minimal manual annotation, demonstrating superior results on both dense agricultural wheat head images and the general-purpose COCO dataset.
This paper introduces SamS, an efficient algorithm that adaptively schedules training samples in Direct Preference Optimization based on the model's evolving batch-wise states, significantly improving LLM alignment performance without modifying the core DPO algorithm or incurring substantial computational overhead.
This paper introduces MeRF, a method that enhances reinforcement finetuning of large reasoning models by injecting reward specifications directly into prompts as "motivation," thereby leveraging in-context learning to align generation with optimization objectives and achieve substantial performance gains over standard RLVR baselines.
The paper proposes SUBARU, a power-efficient framework for hearables that intentionally employs sub-Nyquist sampling and low bit-resolution ADCs to achieve a 3.31x reduction in power consumption while maintaining high-quality multimodal speech enhancement through a novel wideband reconstruction methodology.
LD-RPS proposes a novel, dataset-free, and unified image restoration framework that leverages recurrent posterior sampling on a pretrained latent diffusion model, enhanced by multimodal semantic priors and a lightweight alignment module, to achieve superior performance across various degradation types without task-specific training.
This paper establishes that Physics-Informed Neural Networks (PINNs) require a network size scaling with the number of noisy samples to achieve empirical risk below the noise variance, demonstrating that simply increasing data quantity cannot compensate for insufficient model capacity in noisy PDE training.
This paper proposes MCULoRA, a novel parameter-efficient framework featuring modality combination aware low-rank adaptation and dynamic parameter fine-tuning to resolve gradient conflicts and improve performance in incomplete multimodal emotion recognition.
This paper identifies a pervasive "agreement bias" in Multimodal LLM verifiers that causes them to over-validate agent behavior, and proposes a lightweight Self-Grounded Verification (SGV) method that significantly improves failure detection and task completion across web navigation, computer use, and robotics by decoupling prior generation from trajectory evaluation.
The paper proposes Mamba Snake, a novel deep snake framework enhanced by state space modeling and a dual-classification synergy mechanism, which effectively addresses the challenges of multi-scale structural heterogeneity in Unified Medical Image Segmentation by modeling inter-organ topological relationships and refining complex morphologies to achieve superior performance across five clinical datasets.
This paper introduces InsightX Agent, a novel Large Multimodal Model-based agentic framework that integrates a Sparse Deformable Multi-Scale Detector with an Evidence-Grounded Reflection tool to achieve reliable, interpretable, and interactive X-ray non-destructive testing analysis, demonstrated by a 96.54% F1-score on the GDXray+ dataset.
This paper proposes a Vision Transformer-based framework that leverages PCA-driven weak supervision to expand limited manual annotations for refining disaster-affected area segmentation using Sentinel-2 and Formosat-5 imagery, thereby enhancing the reliability and scalability of the Taiwan Space Agency's Emergent Value Added Product (EVAP) in scenarios with scarce ground truth.
This paper presents the first comprehensive survey of flow matching applications in biology and life sciences, systematically reviewing its theoretical foundations and categorizing its recent advancements in biological sequence modeling, molecule design, and protein generation.
This paper introduces User Goal State Tracking (UGST), a novel framework and three-stage methodology that enables LLM-based user simulators to autonomously track goal progression and generate goal-aligned responses, significantly improving performance on MultiWOZ 2.4 and -Bench benchmarks.
The paper introduces CauKer, a novel algorithm that combines Gaussian Process kernel composition with Structural Causal Models to generate diverse, causally coherent synthetic time series, enabling sample-efficient pre-training of classification foundation models that exhibit clear scaling laws across varying dataset sizes and model capacities.
GraphProp is a two-phase framework for training graph foundation models that first learns structural generalization by predicting graph invariants and then leverages these representations as positional encodings to enhance cross-domain performance in graph-level tasks, particularly outperforming existing methods in scenarios with limited data or missing node attributes.
Video-EM introduces a training-free, event-centric episodic memory framework that enhances long-form video understanding by orchestrating an LLM to localize, segment, and refine query-relevant moments into a compact, temporally coherent event timeline, thereby overcoming the context limitations of existing Video-LLMs without requiring architectural changes.