Posters

This paper presents a new auditing method for DP-SGD that provides substantially tighter black-box privacy analyses than previous methods, yielding significantly closer empirical estimates to theoreti…

This research establishes the first minimax optimal algorithm for submodular maximization with bandit feedback, achieving a regret bound matching the lower bound.

This paper presents OFU-MNL+, a constant-time algorithm achieving nearly minimax optimal regret for contextual multinomial logistic bandits, closing the gap between existing upper and lower bounds.

NEST, a novel semi-parametric language model, significantly boosts LLM generation quality, provides accurate source attribution, and achieves a 1.8x speedup in inference time by cleverly incorporating…

Contrastive Divergence algorithms achieve near-optimal parameter estimation rates, matching the Cramér-Rao lower bound under specific conditions, as proven by a novel non-asymptotic analysis.

Clipped SGD achieves near-optimal sub-Gaussian rates for high-dimensional heavy-tailed statistical estimation in streaming settings, improving upon existing state-of-the-art results.

Near-optimal dynamic regret is achieved for adversarial linear mixture MDPs with unknown transitions, bridging occupancy-measure and policy-based methods for superior performance.

This paper presents near-optimal sample complexity bounds for solving distributionally robust reinforcement learning problems with general Lp norms, showing robust RL can be more sample-efficient than…

SVOGS: Near-optimal distributed minimax optimization is achieved under second-order similarity, balancing communication, computation, and achieving near-optimal complexities.

New distributional RL algorithm (DCFP) achieves near-minimax optimality for return distribution estimation in the generative model regime.

Researchers discover ‘safety basins’ in LLMs, proposing a new metric (VISAGE) to quantify finetuning risks and visualize how these basins protect against safety compromise during model training.

ParamRepulsor, a novel parametric dimensionality reduction method, achieves state-of-the-art local structure preservation by mining hard negatives and using a tailored loss function.

SPARTEX achieves memory-efficient extreme multi-label classification by integrating dynamic sparse training with an auxiliary loss function, enabling end-to-end training with millions of labels on com…

ChemFlow: a new framework efficiently explores chemical space using latent flows, unifying existing methods & incorporating physical priors for molecule manipulation and optimization.

Sparse navigable graphs enable efficient nearest neighbor search, but their construction and limits in high dimensions remain unclear. This paper presents an efficient method to construct navigable gr…

Inspired by nature, researchers introduce a novel spatiotemporal local algorithm for machine learning that outperforms backpropagation in online learning scenarios with limited data or long video stre…

This paper proposes ’natural counterfactuals’ for more realistic counterfactual reasoning in AI, using backtracking to minimize deviations from observed data while ensuring feasibility.

NaRCan: High-quality video editing via diffusion priors and hybrid deformation fields.

New algorithm, POAM, excels at multi-agent cooperation by adapting to diverse and changing teammates in dynamic scenarios.

MVSplat360: Generating stunning 360° views from just a few images!