Posters

Visual tokens boost long-text multi-modal models!

ProtoSurv uses heterogeneous graph representation learning to predict cancer survival more accurately by incorporating tumor heterogeneity and tissue spatial relationships from WSIs.

SeeX, a novel bi-level optimization framework, effectively tackles the challenge of exploration in visually cluttered environments by training a separated world model to extract relevant information a…

New gradient coding protocols efficiently leverage partial results from slow worker nodes, accelerating distributed training by approximately 2x and significantly improving accuracy.

ProMaC leverages MLLM hallucinations in an iterative framework to generate precise prompts for accurate object segmentation, minimizing manual prompt dependency.

This paper presents a fully automated method for PDDL translation and planning using LLMs and environment interaction, achieving a 66% success rate on challenging PDDL domains.

Drifted VESDE: Faster convergence, efficient sampling for variance-exploding diffusion models!

GCFormer, a novel graph Transformer, enhances node representation learning by employing a hybrid token generator and contrastive learning, outperforming existing methods on various datasets.

BeatDiff, a lightweight diffusion model, reconstructs ECG morphology from indirect signals, enabling noise removal, artifact reduction, missing-lead recovery, and anomaly detection.

Lever-LM configures effective in-context demonstrations for large vision-language models using a small language model, significantly improving their performance on visual question answering and image …

LESS achieves state-of-the-art Referring 3D Segmentation using only binary masks, significantly reducing labeling effort and improving efficiency with a novel single-stage pipeline.

Conformal Prediction with Length Optimization (CPL) achieves shorter, conditionally valid prediction sets by optimizing length while ensuring coverage across various covariate shifts.

LEDEX: A novel training framework significantly boosts LLMs’ code self-debugging by using automated data collection, supervised fine-tuning, and reinforcement learning, leading to more accurate code a…

Under-parameterized linear regression models can surprisingly exhibit double descent, contradicting traditional bias-variance assumptions.

Learning-to-Cache (L2C) dramatically accelerates diffusion transformers by intelligently caching layer computations, achieving significant speedups with minimal performance loss.

This paper introduces learning-augmented priority queues, using predictions to boost efficiency and optimality, achieving significant performance gains over traditional methods.

Leveraging predictions, this paper presents a novel algorithm for dynamic submodular maximization achieving significantly faster update times (O(poly(log n, log w, log k)) amortized) compared to exist…

This paper shows how noisy predictions about optimal solutions can improve approximation algorithms for NP-hard problems like MAX-CUT, exceeding classical hardness bounds.

This paper introduces a novel framework for learning-augmented algorithms that improves performance by integrating the learning process into the algorithm itself, rather than treating the predictor as…

PFSUM, a novel learning-augmented algorithm, leverages short-term predictions to achieve superior performance in solving the Bahncard problem, outperforming existing methods with improved consistency …