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 introduces CrossMPI, a novel cross-modal prompt injection attack that uses image-only perturbations to steer the interpretation of both textual and visual inputs in Large Vision-Language Mod…

The paper introduces S2MDF, a plug-and-play module that enforces a hard constraint to eliminate interpenetrations in multi-object Signed Distance Field (SDF) representations, significantly improving p…

The paper introduces Confidence-Adaptive SwiGLU ($κ$-SwiGLU), a novel gating mechanism for Mixture-of-Experts (MoE) models that dynamically adjusts the gate sharpness based on token-level routing conf…

The paper proposes Cert-LAS, a novel certified method for verifying model ownership in text-to-image diffusion models, which is robust against malicious signal removal attacks.

The paper introduces MIRAGE, a framework that systematically discovers semantic attacks on online HD map construction by finding plausible environmental variations that bypass standard adversarial def…

The paper introduces MIRAGE, a novel pipeline that generates context-aware prompt injection attacks by embedding malicious text into user-generated content regions of mobile screenshots, successfully…

The paper introduces MIRAGE, a novel pipeline that generates context-aware prompt injection attacks by injecting malicious text into user-generated content regions of mobile screenshots, successfully…

The paper introduces Staged Executable Inverse Graphics (SEIG), an agentic framework that uses general-purpose Vision-Language Models (VLMs) to reconstruct editable 3D scenes directly into executable…

The paper proposes BRACS, a training-free steering framework that adaptively corrects visual grounding failures in large vision-language models, significantly reducing object hallucination without sac…

The paper argues that using confidence-based decoding, which is optimized via training mask alignment, fundamentally misaligns Masked Diffusion Models (MDMs) from the logical flow needed for complex r…

The paper introduces PRISM, a method for decoding preference signals from noisy latents using a lightweight Query-based Aggregation head and a frozen video diffusion backbone, achieving state-of-the-a…

This paper systematically analyzes how different architectural components of Large Vision-Language Models (LVLMs) contribute to hallucination robustness, finding that joint enhancement of visual fidel…

The paper introduces Robust Prior Update (RPU), a module that improves the faithfulness of diffusion-based inverse solvers by stabilizing the prior update step, thereby reducing measurement-conditione…

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.

PixVOD proposes a fully parallelizable, pixel-distributed framework for visual odometry and depth estimation that performs computations directly on the sensor using Gaussian Belief Propagation.

The paper proposes a method for bit-exact verification of AI inference outputs without sacrificing performance, demonstrating that deterministic, precise re-computation is possible even across differe…

The paper proposes combining Gaussian noise and bilateral filtering into a simple preprocessor that achieves supralinear and scalable adversarial robustness in CNNs with significantly reduced computat…