Posters

Leveraging symmetry in automated equation discovery improves accuracy and simplicity of learned governing equations, enhancing robustness against noise and achieving higher success rates across divers…

Researchers unveil a novel algorithm for high-dimensional symmetric linear bandits, achieving a regret bound of O(d^(2/3)T^(2/3)log(d)), surpassing limitations of existing approaches that assume expli…

SymILO: A novel symmetry-aware learning framework dramatically improves integer linear program (ILP) solutions by addressing data variability caused by ILP symmetry.

LASR, a novel symbolic regression method, uses zero-shot LLM queries to discover and evolve abstract concepts, substantially outperforming state-of-the-art approaches and discovering a new LLM scaling…

SWT-Bench, a new benchmark, reveals that LLMs excel at generating tests for real-world bug fixes, surpassing dedicated test generation systems and significantly improving code-fix precision.

SwitchHead: A novel MoE attention mechanism accelerates Transformers by significantly reducing computation and memory, matching baseline performance.

Swift Sampler (SS) automates the learning of efficient data samplers for deep learning, achieving significant performance gains (e.g., 1.5% on ImageNet) with minimal computational cost using only 10 p…

SWE-agent achieves state-of-the-art performance on software engineering benchmarks by creating a custom agent-computer interface that enhances LM agents’ ability to use computers.

SVFT: a novel parameter-efficient fine-tuning method achieves near full fine-tuning accuracy using only 0.006% to 0.25% of parameters, significantly outperforming existing techniques.

Deep learning’s Adam-style optimizers exhibit a surprising surge phenomenon: optimal learning rates initially increase, then decrease, before converging to a non-zero value as batch size grows.

SureMap, a new method, significantly boosts accuracy in single and multi-task disaggregated evaluations of AI models using limited data by transforming the problem into Gaussian mean estimation and cl…

SLATE: Supra-Laplacian encoding for spatio-temporal Transformers achieves state-of-the-art dynamic link prediction by innovatively using a multi-layer graph representation and a unique cross-attention…

Boosting diffusion model features: This paper introduces GATE, a novel method to suppress ‘content shift’ in diffusion features, improving their quality via off-the-shelf generation techniques.

SuperVLAD: A new visual place recognition method boasts superior robustness and compactness, outperforming state-of-the-art techniques by significantly reducing parameters and dimensions.

Supervised Kernel Thinning accelerates kernel regression by cleverly compressing data, achieving quadratic speedups in training and inference with minimal accuracy loss.

Generate multiple text drafts from a single language model pass with Superposed Decoding, significantly boosting efficiency!

SuperDeepFool: a fast, accurate algorithm generating minimal adversarial perturbations, significantly improving deep learning model robustness evaluation and adversarial training.

Neural network hyperparameter transferability across vastly different model sizes is achieved via a newly discovered property called ‘Super Consistency’ of loss landscapes.

KF-GVD: a novel knowledge fusion-based method boosts vulnerability detection accuracy by integrating task-specific knowledge into graph neural networks, achieving significant performance gains and dis…

This paper introduces Subwords as Skills (SaS), a fast and efficient skill extraction method for sparse-reward reinforcement learning that uses tokenization. SaS enables 1000x faster skill extraction…