Low-Pass Flow Matching introduces a spectral bias into the flow matching process, allowing it to better model natural data by transitioning from a standard source spectrum to a frequency-decaying bias…

The paper demonstrates that for FFT-based radar imaging on Apple Silicon, the limiting factor for half-precision (FP16) is dynamic range, not mantissa precision, and proposes a block-floating-point (B…

The paper introduces Texture++, a framework for enhancing low-resolution textures in 3D assets using a diffusion-based super-resolution model and adaptive view selection strategy.

This paper systematically characterises the sensitivity of emergent misalignment (EM) in LLMs to various training choices, finding that the choice of optimiser has the largest effect on misalignment r…

This paper introduces IR275K, a curated benchmark for multi-frame super-resolution in infrared remote sensing, and evaluates CGMamba, a lightweight state-space model, achieving state-of-the-art perfor…

The paper introduces Text-Conditioned Layer-wise Internal Alignment (TC-LIA), a model-agnostic method that significantly improves the detection of 'mirage'—when Vision-Language Models confidently answ…

The paper investigates whether using fine-grained, tensorized adapters (CP components) instead of standard LoRA ranks improves the accuracy-budget trade-off in PEFT, finding that while they fill budge…

The paper proposes a Variational Adapter (VACSR) to improve cross-modal similarity representation by treating fine-grained image-text matching as a variational inference problem, thereby mitigating th…

This paper introduces LiteMatch, a lightweight stereo matching framework that achieves strong zero-shot generalization through cost volume stabilization without expensive 3D convolutions.

This paper investigates the application of Parameter-Efficient Fine-Tuning (PEFT) methods, specifically adapters and LoRA, to large pretrained models for instance segmentation, demonstrating that thes…

Replacing global self-attention in stereo transformers with a data-independent Walsh-Hadamard token mixer reduces compute and latency by a factor of 2.46 and 2.65 respectively.

The paper introduces LL-Bench, a comprehensive benchmark for evaluating large-scale generative models on low-level vision tasks, and proposes LL-Score, an MLLM-based evaluator that better aligns quali…

The paper proposes a deterministic, version-aware aggregation method that significantly outperforms existing LLM-based systems for resolving memory conflicts in fact consolidation tasks.

The paper proposes Progressive Loading-Aware Hierarchical Contrastive Learning (PL-HCL), a framework to detect misalignment between a skill's description and its true behavior in large language model…

The paper identifies a fundamental mismatch between standard pairwise ranking metrics (like AP and FPR-95) and the true assignment objective in multi-view object association, proposing a Sinkhorn-base…

The paper demonstrates that audio-language models often ignore conflicting audio evidence in favor of text, and proposes a training-free decoding rule, GACL, that significantly improves faithfulness b…

The paper proposes a unified framework to systematically redefine instance matching for Panoptic Quality evaluation, moving beyond the standard One-to-One matching to accommodate complex scenarios lik…

The paper proposes a multi-resolution end-to-end deep neural network for autonomous driving that dynamically adjusts input resolution to optimize the critical tradeoff between prediction accuracy and…

The paper introduces SynCity 3000, a framework for generating large, coherent 3D scenes using a convolutional generator, addressing the scarcity of 3D scene data for training.