Posters

Warm-up-free policy optimization achieves rate-optimal regret in linear Markov decision processes, improving efficiency and dependence on problem parameters.

This research introduces the first theoretical guarantees for warm-starting the celebrated Push-Relabel network flow algorithm, improving its speed using a predicted flow, while maintaining worst-case…

WAGLE: A novel weight attribution-guided LLM unlearning framework boosts unlearning performance by strategically identifying and manipulating influential model weights, achieving a better balance betw…

VQ-Map leverages vector quantization to estimate bird’s-eye-view maps with unprecedented accuracy, setting new benchmarks.

VPNet, a novel semantic scene completion network, uses multi-frame knowledge distillation and confident voxel proposals to improve accuracy and handle dynamic aspects of 3D scenes from point clouds, a…

VLMimic: Vision-Language Models enable robots to master intricate actions using only a few human video demonstrations, surpassing existing methods by a significant margin.

VLG-CBM enhances concept bottleneck models with vision-language guidance for faithful interpretability and improved accuracy.

Vivid-ZOO: Generating high-quality multi-view videos from text using a novel diffusion model.

VITRON: a unified pixel-level Vision LLM excels in understanding, generating, segmenting, and editing images and videos.

Visual SKETCHPAD empowers multimodal language models (LLMs) with visual reasoning abilities by allowing them to generate intermediate sketches. This innovative framework substantially enhances LLM per…

This paper presents NSP², a novel method for visual prompt tuning in continual learning that leverages orthogonal projection to prevent catastrophic forgetting by tuning prompts orthogonal to previous…

Visual pinwheel centers in the cortex act as efficient geometric saliency detectors, responding faster and stronger to complex spatial textures than other structures.

VLORA: Boosting Multimodal LLMs efficiency by merging visual features into model weights instead of extending input sequences.

Visual Fourier Prompt Tuning (VFPT) leverages the Fast Fourier Transform to seamlessly integrate spatial and frequency information for superior parameter-efficient vision model fine-tuning, even with …

Researchers developed a novel zero-shot EEG-based framework for visual reconstruction using a tailored brain encoder and a two-stage image generation strategy, achieving state-of-the-art performance i…

CONBIAS tackles dataset bias by representing visual data as concept graphs, diagnosing imbalances via clique analysis, and debiasing through targeted data augmentation for improved model generalizatio…

AcFormer, a novel vision-language connector for MLLMs, leverages ‘visual anchors’ to reduce computation cost by ~66% while improving accuracy.

Vista: a novel driving world model achieving high-fidelity prediction and versatile controllability, outperforming state-of-the-art models in generalization and prediction accuracy.

VisMin benchmark evaluates visual-language models’ fine-grained understanding by identifying minimal image-text differences (object, attribute, count, spatial relation). Current VLMs struggle with sp…

VisionLLM v2 unifies visual perception, understanding, and generation, excelling in various vision tasks and achieving performance comparable to task-specific models.