Posters

This research introduces Cluster-guided Sparse Experts (CSE), enabling pretrained language models to effectively learn long-tail domain knowledge without domain-specific pretraining, thus achieving su…

New large-scale dataset and model boost on-road object importance estimation accuracy by 23.1%!

New algorithms achieve optimal weak regret in K-armed dueling bandits by leveraging the full problem structure, improving upon state-of-the-art methods.

This paper presents efficient algorithms for approximating equilibria in non-concave games, focusing on tractable ɸ-equilibria and addressing computational challenges posed by infinite strategy sets.

LLMs’ performance drastically varies depending on prompt phrasing; this paper introduces ROBUSTAL-PACAEVAL to evaluate lower-bound performance via worst-case prompt analysis, revealing model inconsist…

Truncated kernel methods consistently outperform standard methods by eliminating the saturation effect, offering faster learning rates and enhanced theoretical guarantees.

Vision Transformers achieve surprisingly high accuracy by transferring only pre-training attention maps, challenging the conventional belief that feature learning is crucial.

This paper introduces uniform meta-stability for meta-learning, providing tighter generalization bounds for convex and weakly-convex problems, addressing computational limitations of existing algorith…

Researchers rigorously prove the Strong Lottery Ticket Hypothesis, offering the first theoretical guarantees on the sparsity of winning neural network subnetworks.

Giant leap in molecular GNNs! MolGPS, a new foundation model, achieves state-of-the-art performance on molecular property prediction by leveraging massive datasets and demonstrating the scalability o…

Boosting certified robustness of machine learning models by 3-4% using generated data from diffusion models!

High-dimensional spectral algorithms show saturation effects: Kernel Ridge Regression underperforms optimal algorithms like gradient flow when regression functions are very smooth.

New reinforcement learning model clarifies the role of information structure in partially-observable sequential decision-making problems, proving an upper bound on learning complexity.

Transformers’ self-attention mechanism, while powerful, suffers from rank collapse with increasing depth. This paper reveals that while masked attention still leads to exponential collapse, sparse att…

Spectral algorithms for graph bisection show surprising robustness to helpful adversaries in semirandom models, with unnormalized Laplacian consistently outperforming the normalized one.

Small-size Graph Neural Networks effectively solve Linear Programs!

Auto-Regressive Decision Trees (ARDTs) surprisingly outperform Transformers on language tasks!

Researchers achieve full parameter identifiability in partially observed linear causal models using novel graphical conditions and a likelihood-based estimation method, addressing previous limitations…

Researchers discover Dilated Entropy is the optimal distance-generating function for solving extensive-form games using first-order methods, achieving near-optimal regret bounds.

Fragile SGD & Amelie SGD achieve near-optimal speed in decentralized asynchronous optimization, handling diverse worker & communication speeds.