Posters

Real-time rendering of objects with subsurface scattering effects is now possible with SSS-GS, a novel method combining explicit surface geometry and implicit subsurface scattering for high-quality no…

A-Harmonic reward function and Reward Preference Optimization (RPO) improve subject-driven text-to-image generation by enabling faster training and state-of-the-art results with a simpler setup.

SubgDiff enhances molecular representation learning by incorporating substructural information into a diffusion model framework, achieving superior performance in molecular force predictions.

Sub-optimal expert data improves Inverse Reinforcement Learning by significantly reducing ambiguity in reward function estimation.

SAUE: A novel multi-source blended-target domain adaptation approach using style adaptation and uncertainty estimation to improve model robustness and accuracy.

Structured Unrestricted-Rank Matrices (SURMs) revolutionize parameter-efficient fine-tuning by offering greater flexibility and accuracy than existing methods like LoRA, achieving significant gains in…

This AI system generates high-quality multi-track music arrangements from simple lead sheets using a novel style prior modeling approach, significantly improving both efficiency and musical coherence.

Sumba: a novel forecasting model achieves up to 8.5% improvement by using a structured matrix basis to generate dynamic spatial structures with lower variance and better interpretability.

Predicting outcomes of combined sequential interventions is challenging, especially in sparse data. This paper introduces CSI-VAE, a novel compositional model that provides reliable predictions for u…

Neuromodulated RNNs (NM-RNNs) enhance RNN flexibility by dynamically scaling recurrent weights using a neuromodulatory subnetwork, achieving higher accuracy and generalizability on various tasks compa…

SICSM, a novel framework, integrates selective SSMs and GFNs to accurately infer complex dynamical system structures from irregularly sampled, partially observed trajectories.

Fine-tuning, even on a single demonstration, effectively uncovers hidden LLM capabilities, surpassing simple prompting methods.

StreamingDialogue revolutionizes prolonged dialogue learning by compressing long contexts into conversational attention sinks, minimizing information loss and achieving a 4x speedup with 18x less memo…

VideoStreaming, a novel vision-language model, enables efficient and accurate understanding of arbitrarily long videos using a constant number of tokens via streaming encoding and adaptive memory sele…

SB-GFlowNets: Streaming Bayesian inference is now efficient and accurate using GFlowNets, enabling real-time model updates for large, sequential datasets.

StreamFlow accelerates video optical flow estimation by 44% via a streamlined in-batch multi-frame pipeline and innovative spatiotemporal modeling, achieving state-of-the-art results.

Stratified Prediction-Powered Inference (StratPPI) significantly improves language model evaluation by combining human and automated ratings, using stratified sampling for enhanced accuracy and tighte…

StrategyLLM uses four LLM agents to generate consistent, generalizable few-shot prompts, significantly improving LLM problem-solving performance across various tasks.

Incentive-aware algorithm achieves low regret in strategic multi-armed bandits under debt-free reporting, establishing truthful equilibrium among arms.

This paper introduces the Strategic Littlestone Dimension, a novel complexity measure for online strategic classification, proving instance-optimal mistake bounds in the realizable setting and improve…