Posters

Goal-conditioned RL gets a temporal upgrade with compositional DFAs (cDFAs), enabling zero-shot generalization and faster policy specialization via novel graph neural network embeddings and reach-avoi…

LLM-directed compositional 3D-aware video generation (C3V) achieves high-fidelity video generation with diverse motion and flexible concept control by decomposing prompts, generating 3D concepts, and …

Researchers developed a novel method using mechanistic interpretability to create compact formal proofs for AI model performance, improving AI safety and reliability.

MINITRON: Efficiently creating smaller, high-performing LLMs via pruning & distillation, slashing training costs by up to 40x!

Node2Vec, a popular network embedding method, is proven to consistently recover community structure in stochastic block models, paving the way for more reliable unsupervised community detection.

Communication-efficient algorithms for federated group distributionally robust optimization (FGDRO) are introduced, achieving lower communication complexity and superior performance on real-world task…

Distributed Lion: Training large AI models efficiently by communicating only binary or low-precision vectors between workers and a server, significantly reducing communication costs and maintaining co…

This paper presents communication-efficient protocols for the distributed experts problem, achieving near-optimal regret with theoretical and empirical validation.

CoMERA achieves 2-3x faster AI model training via rank-adaptive tensor optimization, significantly improving both computing and memory efficiency.

Boosting neural network prediction reliability, this research ingeniously combines statistical depth and Fermat distance for superior uncertainty quantification, eliminating the need for distributiona…

LE-SINR combines Wikipedia species descriptions with citizen science observations to create accurate species range maps, even with limited data, outperforming existing methods.

CoMat: Aligning text-to-image diffusion models using image-to-text concept matching for superior text-image alignment.

AutoPalette: a new framework minimizing color redundancy in dataset distillation, resulting in more efficient model training with comparable performance.

Collaborative Video Diffusion (CVD) generates multiple consistent videos from various camera angles using a novel cross-video synchronization module, significantly improving consistency compared to ex…

Collaborative Refining for Learning from Inaccurate Labels (CRL) refines data using annotator agreement, improving model accuracy with noisy labels.

Coral: a novel collaborative cognitive diagnosis model uses disentangled representation learning to improve diagnostic accuracy by leveraging collaborative signals among learners with similar learning…

A novel Collaborative Neural Framework (CNF) enhances the robustness of neural vehicle routing methods against adversarial attacks by collaboratively training multiple models and intelligently distrib…

ColJailBreak cleverly circumvents AI safety filters by first generating safe images and then subtly injecting unsafe content using image editing.

COLD framework rigorously evaluates LLMs’ causal reasoning in everyday scenarios using 9 million causal queries derived from human-generated scripts of daily activities.

Coherent 3D scenes are diffused from a single RGB image using a novel image-conditioned 3D scene diffusion model, surpassing state-of-the-art methods.