Posters

Energy-based Navigation Policy (ENP) revolutionizes Vision-Language Navigation by modeling joint state-action distributions, achieving superior performance across diverse benchmarks.

Vision-language models effectively detect noisy labels, improving image classification accuracy with DEFT.

OoD-ViT-NAS: a new benchmark reveals how ViT architecture impacts out-of-distribution generalization, highlighting the importance of embedding dimension and challenging the reliance on in-distribution…

Latent Compression Learning (LCL) revolutionizes vision model pre-training by effectively leveraging readily available interleaved image-text data, achieving performance comparable to models trained o…

Vision Mamba Mender systematically optimizes the Mamba model by identifying and repairing internal and external state flaws, significantly improving its performance in visual recognition tasks.

VFM-6D: a novel framework achieving generalizable object pose estimation for unseen categories by leveraging vision-language models.

VISA, a new variational inference method, significantly speeds up approximate inference for complex models by reusing model evaluations across multiple gradient steps, achieving comparable accuracy wi…

Unsupervised learning framework enables high-fidelity non-line-of-sight (NLOS) imaging from irregularly undersampled transients, surpassing state-of-the-art methods in speed and robustness.

VidMan: a novel framework leverages video diffusion models and a two-stage training mechanism to significantly improve robot manipulation precision by effectively using robot trajectory data and impli…

VideoTetris: a novel framework enabling compositional text-to-video generation by precisely following complex textual semantics through spatio-temporal compositional diffusion, achieving impressive qu…

VIDEOLLM-MOD boosts online video-language model efficiency by selectively skipping redundant vision token computations, achieving ~42% faster training and ~30% memory savings without sacrificing perfo…

Researchers boost long-form video understanding efficiency by 6.89x and reduce memory usage by 84% using a novel learnable video token merging algorithm.

Training-free video motion control achieved via novel Motion Feature (MOFT) extraction from existing video diffusion models, offering architecture-agnostic insights and high performance.

VFIMamba uses state-space models for efficient and dynamic video frame interpolation, achieving state-of-the-art results by introducing a novel Mixed-SSM Block and curriculum learning.

VeXKD: A versatile framework boosts 3D perception by cleverly combining cross-modal fusion and knowledge distillation, improving single-modal student model accuracy without extra inference time.

Learning verified safe neural network controllers for complex nonlinear systems is now possible, achieving an order of magnitude longer safety horizons than state-of-the-art methods while maintaining …

LLMLIFT: An LLM-powered approach builds verified lifting tools for DSLs, outperforming prior symbolic methods in benchmark transpilation and requiring less development effort.

VRCP, a new framework, uses neural network verification to make conformal prediction robust against adversarial attacks, supporting various norms and regression tasks.

VeLoRA: Train massive LLMs efficiently by compressing intermediate activations!

VQ-Prompt uses vector quantization to optimize discrete prompts for continual learning, achieving state-of-the-art performance by effectively abstracting task knowledge and optimizing prompt selection…