Posters

Researchers unveil stealth edits for large language models, offering a new metric to assess editability and reveal vulnerability to malicious attacks.

Density estimation algorithms face inherent trade-offs: reducing sample needs often increases query time. This paper proves these trade-offs are fundamental, showing limits to how much improvement is…

Regularized Kernel Kullback-Leibler divergence solves the original KKL’s disjoint support limitation, enabling comparison of any probability distributions with a closed-form solution and efficient gra…

State-free Reinforcement Learning (SFRL) framework eliminates the need for state-space information in RL algorithms, achieving regret bounds independent of the state space size and adaptive to the rea…

GRAPHSSM: a novel graph state space model efficiently captures temporal graph dynamics, overcoming limitations of existing sequence models.

State Chrono Representation (SCR) enhances reinforcement learning generalization by incorporating extensive temporal information and cumulative rewards into state representations, improving performanc…

START, a novel SSM-based architecture with saliency-driven token-aware transformation, achieves state-of-the-art domain generalization performance with efficient linear complexity.

Star-Agents automates data optimization for instruction-tuned LLMs via multi-agent collaboration, achieving a 12% average performance boost.

Stable-Pose: Precise human pose guidance for text-to-image synthesis.

ZAF: a novel replay-free continual learning method for vision-language models, significantly reduces forgetting by stabilizing zero-shot predictions.

Weighted reservoir sampling stabilizes online learning algorithms by creating a robust ensemble of intermediate solutions, significantly improving accuracy and mitigating sensitivity to outliers.

DiGIT stabilizes image autoregressive models’ latent space using a novel discrete tokenizer from self-supervised learning, achieving state-of-the-art image generation.

Sharper ASGD generalization bounds achieved by leveraging on-average model stability, even without Lipschitz and smoothness assumptions; validated with diverse machine learning models.

This paper provides novel theoretical guarantees for adversarial training of shallow neural networks, improving generalization bounds via early stopping and Moreau’s envelope smoothing.

D³GM, a novel score-based diffusion model, enhances stability & generalizability in solving inverse problems by leveraging measure-preserving dynamics, enabling robust image reconstruction across dive…

STk: a novel, differentiable module solves Top-k problems in neural networks without extra time/GPU memory, boosting performance in long-tailed learning.

SSDM: Scalable Speech Dysfluency Modeling tackles challenges in speech dysfluency analysis by using articulatory gestures for scalable alignment, a connectionist subsequence aligner for efficient dysf…

SSDiff: A novel spatial-spectral integrated diffusion model for superior remote sensing pansharpening.

SSA-Seg improves semantic segmentation by adapting pixel-level classifiers to the test image’s semantic and spatial features, achieving state-of-the-art performance with minimal extra computational co…

SS1: A novel GPU-friendly operator accelerates deep learning inference by leveraging structured parameter sharing, achieving superior quality-efficiency tradeoffs compared to existing methods.