Posters

AI agents learn to cooperate effectively even when individual and group goals clash using the new Altruistic Gradient Adjustment (AgA) algorithm.

This paper presents novel informational results and a new algorithm (‘Ping-Pong’) for solving the Procrustes-Wasserstein problem, significantly advancing high-dimensional data alignment.

Diffusion-KTO: Aligning text-to-image models with human preferences using simple likes/dislikes, maximizing expected human utility.

Efficient Diffusion Alignment (EDA) leverages pretrained diffusion models and Q-functions for efficient continuous control, exceeding all baselines with minimal annotation.

AVAgent uses an LLM-driven workflow to intelligently align audio and visual data, resulting in improved AV joint representations and state-of-the-art performance on various downstream tasks.

MambaNO: a novel neural operator achieving linear complexity and state-of-the-art accuracy in solving PDEs by cleverly balancing global and local information using an alias-free architecture.

ALI-Agent uses LLM-powered agents for in-depth, adaptive assessment of LLMs’ alignment with human values, overcoming limitations of existing static benchmarks.

Language model algorithms have improved drastically, halving compute needs every 8 months since 2012, surpassing Moore’s Law; however, compute scaling, not algorithms, drove most recent performance ga…

Fans can massively boost an artist’s song exposure on music streaming platforms by strategically placing it in their playlists, achieving up to 40x more recommendations.

Randomly initialized transformers, with only embedding layers optimized, surprisingly excel at various algorithmic tasks, revealing inherent capabilities even before training.

AlchemistCoder enhances code LLMs by pioneering hindsight tuning on multi-source data, harmonizing conflicting styles via AlchemistPrompts, and achieving state-of-the-art performance.

AirSketch generates aesthetically pleasing sketches directly from noisy hand-motion tracking data using a self-supervised controllable diffusion model, eliminating the need for expensive AR/VR equipme…

AID, a novel training-free method, significantly improves image interpolation by fusing inner/outer interpolated attention layers and using beta-distribution for coefficient selection, enhancing consi…

AHA: Human-assisted OOD learning maximizes OOD generalization and detection by strategically labeling data in a novel maximum disambiguation region, significantly outperforming existing methods with o…

AGILE, a novel reinforcement learning framework, significantly enhances LLM agents’ performance on complex conversational tasks by integrating memory, tools, expert interactions, and reflection, outpe…

This paper introduces Quantitative Relative Judgment Aggregation (QRJA), a novel social choice model, and applies it to ranking prediction, yielding effective and interpretable results on various real…

Aggregate-and-Adapt Prompt Embedding (AAPE) boosts CLIP’s downstream generalization by distilling textual knowledge from natural language prompts, achieving competitive performance across various visi…

AGENTPOISON: A novel backdoor attack compromises LLM agents by poisoning their memory or knowledge bases, achieving high success rates with minimal performance impact.

This paper introduces a parametric World Knowledge Model (WKM) to improve AI agent planning by integrating both global task knowledge and dynamic state knowledge, thereby overcoming current LLMs’ limi…

WSAC, a novel algorithm, robustly optimizes safe offline RL policies using adversarial training, guaranteeing improved performance over reference policies with limited data.