Posters

BAM! Efficiently upcycles pre-trained models into powerful Mixture-of-Experts (MoE) models, achieving state-of-the-art performance with reduced computational costs.

Longer context in RL boosts generalization but slows down learning; this paper reveals the crucial tradeoff and offers theoretical insights.

BAKU: A simple transformer enables efficient multi-task robot policy learning, achieving 91% success on real-world tasks with limited data.

BAdam: A memory-efficient optimization method enabling full parameter fine-tuning of large language models using a block coordinate descent framework with Adam’s update rule, achieving comparable or s…

BackdoorAlign defends against fine-tuning-based LLM jailbreaks using a ‘backdoor trigger’ to enforce safety alignment during inference, effectively mitigating risks with minimal additional safety exam…

Despite their brittleness, continuous attractors remain functionally robust analog memory models due to persistent slow manifolds surviving bifurcations, enabling accurate approximation and generaliza…

B’MOJO: A novel hybrid architecture for foundation models enhances transductive inference by dynamically balancing eidetic and fading memory, leading to efficient and accurate processing of long seque…

B-cosification: cheaply transform any pre-trained deep neural network into an inherently interpretable model.

B-ary Tree Push-Pull (BTPP) achieves linear speedup for distributed learning on heterogeneous data, significantly outperforming state-of-the-art methods with minimal communication.

AWT: a novel framework boosts vision-language model’s zero-shot capabilities by augmenting inputs, weighting them dynamically, and leveraging optimal transport to enhance semantic correlations.

AUF-MICNS: A novel sequential method efficiently solves the avoiding undesired future problem by dynamically updating influence relations in non-stationary environments while minimizing action costs.

AverNet: All-in-one video restoration defying time-varying unknown degradations.

Deep Neural Collapse (DNC) explained via Average Gradient Outer Product (AGOP).

AVATAR: A novel automated framework optimizes LLM agents for effective tool usage via contrastive reasoning, significantly boosting performance on complex tasks.

AV-GS: A novel Audio-Visual Gaussian Splatting model, uses geometry and material-aware priors to efficiently synthesize realistic binaural audio from a single audio source.

AV-Cloud: Real-time, high-quality 3D spatial audio rendering synced with visuals, bypassing pre-rendered images for immersive virtual experiences.

AutoTimes repurposes LLMs as autoregressive time series forecasters, achieving state-of-the-art results with minimal trainable parameters and faster training/inference.

AutoSurvey automates comprehensive literature survey creation using LLMs, overcoming challenges of context limitations and knowledge constraints via a novel, efficient, and rigorously evaluated method…

PASPO: a novel autoregressive policy optimization method for constrained allocation tasks guarantees constraint satisfaction and outperforms existing methods.

Autoregressive Image Diffusion (AID) generates coherent MRI image sequences from undersampled data, outperforming standard diffusion models by exploiting inter-image dependencies.