arXiv:2412.03671v3 Announce Type: replace-cross Abstract: Performative prediction is a framework accounting for the shift in the data distribution induced by the prediction of a model deployed in the real world. Ensuring rapid convergence to a stable solution where the data distribution remains the same after the model deployment is crucial, especially in evolving environments. This […]
Hexcute: A Compiler Framework for Automating Layout Synthesis in GPU Programs
arXiv:2504.16214v3 Announce Type: replace-cross Abstract: Efficient GPU programming is crucial for achieving high performance in deep learning (DL) applications. The performance of GPU programs depends on how data is parallelized across threads and arranged within memory subsystems. The mapping functions describing tensors on GPUs are known as emphtensor layouts. Low-level programming frameworks, such as CUTLASS […]
Bridging Weakly-Supervised Learning and VLM Distillation: Noisy Partial Label Learning for Efficient Downstream Adaptation
arXiv:2506.03229v3 Announce Type: replace-cross Abstract: In the context of noisy partial label learning (NPLL), each training sample is associated with a set of candidate labels annotated by multiple noisy annotators. With the emergence of high-performance pre-trained vision-language models (VLMs) such as CLIP, LLaVA, and GPT-4V, leveraging these models to replace time-consuming manual annotation and enable […]
FastDINOv2: Frequency Based Curriculum Learning Improves Robustness and Training Speed
arXiv:2507.03779v3 Announce Type: replace-cross Abstract: Large-scale vision foundation models such as DINOv2 boast impressive performances by leveraging massive architectures and training datasets. But numerous scenarios require practitioners to reproduce those pre-training solutions, such as on private data, new modalities, or simply for scientific questioning–which is currently extremely demanding computation-wise. We thus propose a novel pre-training […]
Residual Reservoir Memory Networks
arXiv:2508.09925v2 Announce Type: replace-cross Abstract: We introduce a novel class of untrained Recurrent Neural Networks (RNNs) within the Reservoir Computing (RC) paradigm, called Residual Reservoir Memory Networks (ResRMNs). ResRMN combines a linear memory reservoir with a non-linear reservoir, where the latter is based on residual orthogonal connections along the temporal dimension for enhanced long-term propagation […]
Bridging Performance Gaps for ECG Foundation Models: A Post-Training Strategy
arXiv:2509.12991v2 Announce Type: replace-cross Abstract: ECG foundation models are increasingly popular due to their adaptability across various tasks. However, their clinical applicability is often limited by performance gaps compared to task-specific models, even after pre-training on large ECG datasets and fine-tuning on target data. This limitation is likely due to the lack of an effective […]
Rotary Position Encodings for Graphs
arXiv:2509.22259v3 Announce Type: replace-cross Abstract: We study the extent to which rotary position encodings (RoPE), a recent transformer position encoding algorithm broadly adopted in large language models (LLMs) and vision transformers (ViTs), can be applied to graph-structured data. We find that rotating tokens depending on the spectrum of the graph Laplacian efficiently injects structural information […]
Language Lives in Sparse Dimensions: Toward Interpretable and Efficient Multilingual Control for Large Language Models
arXiv:2510.07213v2 Announce Type: replace-cross Abstract: Large language models exhibit strong multilingual capabilities despite limited exposure to non-English data. Prior studies show that English-centric large language models map multilingual content into English-aligned representations at intermediate layers and then project them back into target-language token spaces in the final layer. From this observation, we hypothesize that this […]
Shaping capabilities with token-level data filtering
arXiv:2601.21571v1 Announce Type: cross Abstract: Current approaches to reducing undesired capabilities in language models are largely post hoc, and can thus be easily bypassed by adversaries. A natural alternative is to shape capabilities during pretraining itself. On the proxy task of removing medical capabilities, we show that the simple intervention of filtering pretraining data is […]
AgenticSimLaw: A Juvenile Courtroom Multi-Agent Debate Simulation for Explainable High-Stakes Tabular Decision Making
arXiv:2601.21936v1 Announce Type: new Abstract: We introduce AgenticSimLaw, a role-structured, multi-agent debate framework that provides transparent and controllable test-time reasoning for high-stakes tabular decision-making tasks. Unlike black-box approaches, our courtroom-style orchestration explicitly defines agent roles (prosecutor, defense, judge), interaction protocols (7-turn structured debate), and private reasoning strategies, creating a fully auditable decision-making process. We benchmark […]
NEAT: Neighborhood-Guided, Efficient, Autoregressive Set Transformer for 3D Molecular Generation
arXiv:2512.05844v2 Announce Type: replace-cross Abstract: Transformer-based autoregressive models offer a promising alternative to diffusion- and flow-matching approaches for generating 3D molecular structures. However, standard transformer architectures require a sequential ordering of tokens, which is not uniquely defined for the atoms in a molecule. Prior work has addressed this by using canonical atom orderings, but these […]
Unheard in the Digital Age: Rethinking AI Bias and Speech Diversity
arXiv:2601.18641v2 Announce Type: replace-cross Abstract: Speech remains one of the most visible yet overlooked vectors of inclusion and exclusion in contemporary society. While fluency is often equated with credibility and competence, individuals with atypical speech patterns are routinely marginalized. Given the current state of the debate, this article focuses on the structural biases that shape […]