Posters

EGSST: a novel framework for event-based object detection, uses graph structures and transformers to efficiently process event data, achieving high accuracy and speed in dynamic scenes.

EGonc, a novel energy-based open-set node classification method, leverages substitute unknowns and energy scores to achieve superior accuracy and robustness in classifying nodes from known classes whi…

EGODE, a novel framework, leverages coupled graph ODEs and an event module to accurately model continuous and instantaneous changes in rigid body dynamics, outperforming existing methods.

EgoChoir: a novel framework harmonizes visual appearance, head motion, and 3D objects to accurately estimate 3D human contact and object affordance from egocentric videos, surpassing existing methods.

EFFI-LEARNER: A novel self-optimization framework dramatically improves the efficiency of LLM-generated code by iteratively refining code based on execution profiles.

This research introduces LFHSIC, a novel, linear-time independence test that significantly outperforms existing methods, especially for high-dimensional data, by learning optimal Fourier feature pairs…

EfficientCAPER: A novel end-to-end framework achieves fast & robust category-level articulated object pose estimation by using a joint-centric approach, eliminating post-processing optimization and en…

BaFormer: a novel boundary-aware Transformer network achieves efficient and accurate temporal action segmentation by using instance and global queries for segment classification and boundary predictio…

STREAM-UGS: a novel semi-streaming algorithm for efficient graphlet sampling, enabling fast analysis of massive graphs with limited memory.

Novel sketching algorithms enable scalable gradient and Hessian analysis for large language models, revealing insights into their intrinsic dimensionality and challenging existing assumptions.

Sign-based optimization gets a speed boost! This paper introduces new algorithms that significantly accelerate convergence in distributed optimization by cleverly using variance reduction and enhanced…

Discover efficient neural pathways for reinforcement learning; drastically reducing model size and energy consumption without sacrificing performance.

Recurrent off-policy RL, while robust, suffers from training instability. RESEL, a novel algorithm, solves this by using a context-encoder-specific learning rate, significantly improving stability an…

TRIPLE: Efficient prompt optimization using fixed-budget best-arm identification.

This paper presents novel graphical criteria and estimators for accurately evaluating policy effectiveness across multiple experimental datasets, even when data distributions differ.

Boost multi-task reinforcement learning with Cross-Task Policy Guidance (CTPG)! CTPG cleverly uses policies from already mastered tasks to guide the learning of new tasks, significantly improving effi…

LoRA-Inlaid: a novel multi-task LLM serving system boosts throughput by 1.58x, latency by 1.76x, and job completion time by 2x, while improving SLO attainment by 10x, all while maintaining model quali…

PromptEval efficiently estimates LLM performance across many prompts, providing robust performance metrics and enabling reliable LLM comparisons.

Fast approximation of Minimum Bayes Risk (MBR) decoding achieved using low-rank matrix completion algorithms, drastically reducing computational cost without sacrificing translation quality.

Learning to rank request outputs improves LLM scheduling, resulting in 2.8x lower chatbot latency and 6.5x higher synthetic data generation throughput.