Posters

Sourcerer: A novel sample-based method for maximum entropy source distribution estimation, resolving ill-posedness while maintaining simulation accuracy.

ProRec, a novel framework, bridges the binary-source semantic gap by using a binary-source encoder-decoder model and LLMs, achieving significant improvements in zero-shot binary summarization and func…

SongCreator: a novel AI system generates complete, high-quality songs from lyrics, surpassing existing methods in lyrics-to-song and lyrics-to-vocals generation.

SDEPO, a new natural policy gradient algorithm, efficiently solves zero-sum Markov games with continuous state spaces, achieving near-optimal convergence independent of state space cardinality.

SHORE: a novel two-stage framework efficiently solves sparse & high-dimensional output regression, boosting interpretability and scalability.

RC-PPO: Reinforcement learning solves minimum-cost reach-avoid problems with up to 57% lower costs!

Revolutionizing inverse problem solving, this paper introduces diffusion optimal control, a novel framework converting signal recovery into a discrete optimal control problem, surpassing limitations o…

Scattered Online Inference (SOI) drastically cuts down ANN computational complexity by leveraging data continuity and prediction seasonality, enabling faster real-time inference on low-power devices.

SOFTS: An efficient MLP-based model for multivariate time series forecasting using a novel STAR module for efficient channel interaction.

Boosting toxicity classification robustness, this paper introduces a novel bi-level optimization framework integrating crowdsourced soft-labels and GroupDRO to enhance resistance against out-of-distri…

Soft Tensor Product Representations (Soft TPRs) revolutionize compositional visual representation learning by seamlessly blending continuous vector spaces and compositional structures, leading to supe…

Soft Superpixel Neighborhood Attention (SNA) optimally denoises images by incorporating superpixel probabilities into an attention module, outperforming traditional methods.

Open-source LLMs are vulnerable to embedding space attacks, which efficiently bypass safety mechanisms and enable data extraction, even after unlearning.

Soft ascent-descent (SoftAD) improves test accuracy and generalization by softening the flooding method, offering competitive accuracy with reduced loss and model complexity.

SocialGPT cleverly leverages Vision Foundation Models and Large Language Models for zero-shot social relation reasoning, achieving competitive results and offering interpretable outputs via prompt opt…

SnapKV: Slashing LLM memory usage & boosting speed via smart KV cache compression!

SMOOTHIE: Label-free LLM routing achieves up to 10% accuracy gains by using a latent variable model to estimate LLM quality without labeled data.

Smoothed online classification can be harder than batch classification when label spaces are unbounded, challenging existing assumptions in machine learning.

Smoothed Energy Guidance (SEG) improves unconditional image generation by reducing self-attention’s energy curvature, leading to higher-quality outputs with fewer artifacts.

AI for science faces hidden biases in causal inference; this paper reveals these flaws using ant behavior data, introducing ISTAnt benchmark, and provides guidelines for more accurate causal AI.