Posters

SequentialAttention++ unites differentiable pruning with combinatorial optimization for efficient and accurate neural network block sparsification, achieving state-of-the-art results.

Sequential Signal Mixing Aggregation (SSMA) boosts message-passing graph neural network performance by effectively mixing neighbor features, achieving state-of-the-art results across various benchmark…

This paper introduces contextual Shtarkov sums, a new complexity measure characterizing minimax regret in sequential probability assignment with contexts, and derives the minimax optimal algorithm, co…

This paper introduces a novel, label-free method for detecting harmful distribution shifts in machine learning models deployed in production environments, leveraging a proxy error derived from an erro…

ExPerior leverages expert demonstrations to enhance online decision-making, even when experts use hidden contextual information unseen by the learner.

Sequence-augmented SE(3)-Flow model, FOLDFLOW-2, excels at generating diverse, designable protein structures, surpassing existing methods in unconditional and conditional design tasks.

Transformers and RNNs show contrasting representational capabilities: Transformers excel at tasks requiring associative recall, while RNNs are better suited for hierarchical language processing. This …

Deep Equilibrium Models (DEQs) outperform standard neural networks, but lack theoretical understanding. This paper provides general separation results showing DEQ’s superior expressivity and character…

SepReformer: Asymmetric encoder-decoder model for efficient speech separation, achieving state-of-the-art performance with less computation.

This paper introduces a novel, tractable semidefinite program (SDP) relaxation for the Gromov-Wasserstein distance, enabling the computation of globally optimal transportation plans.

DANCE, a novel semi-supervised framework, efficiently transfers cell types across multi-omic single-cell data even with limited labeled samples, outperforming current state-of-the-art methods.

New nearly-linear time algorithm achieves high-accuracy semi-random matrix completion, overcoming previous limitations on accuracy and noise tolerance.

HERT: a novel framework for semi-open 3D object retrieval using hierarchical hypergraph equilibrium, achieving state-of-the-art performance on four new benchmark datasets.

SemFlow: A unified framework uses rectified flow to seamlessly bridge semantic segmentation and image synthesis, achieving competitive results and offering reversible image-mask transformations.

SEMCODER: A novel 6.7B parameter code LLM surpasses GPT-3.5-turbo’s performance on code generation and execution reasoning by employing ‘monologue reasoning’—training the model to verbally explain cod…

Emergent communication protocols are surprisingly inconsistent; this paper proves reconstruction-based objectives yield semantically consistent protocols, unlike discrimination-based ones, highlightin…

Learning-based semantic routing, a scalable approach to route planning using rich user queries, is introduced, accompanied by a large-scale public benchmark and a proof-of-concept model demonstrating …

Universal Unsupervised Cross-Domain Retrieval (U2CDR) framework learns semantic features to enable accurate retrieval even when category spaces differ across domains.

SELMA boosts text-to-image fidelity by merging skill-specific models trained on automatically generated image-text datasets.

SelfCodeAlign is a novel self-alignment method for code generation LLMs that surpasses existing methods by avoiding reliance on expensive human annotation or proprietary LLMs. The method achieves thi…