Related papers: EGSS: Entropy-guided Stepwise Scaling for Reliable…

In recent years, large language models (LLMs) achieve remarkable success across a variety of tasks. However, their potential in the domain of Automated Essay Scoring (AES) remains largely underexplored. Moreover, compared to English data,…

Deep learning has emerged as the preferred modeling approach for automatic ECG analysis. In this study, we investigate three elements aimed at improving the quantitative accuracy of such systems. These components consistently enhance…

Systematic generalization remains challenging for current language models, which are known to be both sensitive to semantically similar permutations of the input and to struggle with known concepts presented in novel contexts. Although…

Transparent object perception remains a major challenge in computer vision research, as transparency confounds both depth estimation and semantic segmentation. Recent work has explored multi-task learning frameworks to improve robustness,…

LLMs can solve complex tasks by generating long, multi-step reasoning chains. Test-time scaling (TTS) can further improve performance by sampling multiple variants of intermediate reasoning steps, verifying their correctness, and selecting…

The long-tailed distribution of sequence lengths in LLM serving and reinforcement learning (RL) sampling causes significant computational waste due to excessive padding in batched inference. Existing methods rely on auxiliary models for…

Many scientific problems require multiple distinct computational tasks to be executed in order to achieve a desired solution. We introduce the Ensemble Toolkit (EnTK) to address the challenges of scale, diversity and reliability they pose.…

Test-time scaling (TTS) boosts LLM reasoning via long chain-of-thought (CoT), but the linear KV-cache growth amplifies the memory-bound bottleneck of LLM decoding. Query-aware page-level sparse decoding can achieve state-of-the-art…

Generative skill acquisition enables embodied agents to actively learn a scalable and evolving repertoire of control skills, crucial for the advancement of large decision models. While prior approaches often rely on supervision signals from…

This paper presents a novel sampling scheme for masked non-autoregressive generative modeling. We identify the limitations of TimeVQVAE, MaskGIT, and Token-Critic in their sampling processes, and propose Enhanced Sampling Scheme (ESS) to…

Recent advances in both theory and methods have created opportunities to simulate biomolecular processes more efficiently using adaptive ensemble simulations. Ensemble-based simulations are used widely to compute a number of individual…

Tensor network structure search (TN-SS) aims to automatically discover optimal network topologies and rank configurations for efficient tensor decomposition in high-dimensional data representation. Despite recent advances, existing TN-SS…

Reliable estimates of Gross Primary Productivity (GPP), crucial for evaluating climate change initiatives, are currently only available from sparsely distributed eddy covariance tower sites. This limitation hampers access to reliable GPP…

Equality saturation (EqSat) is a powerful optimization paradigm that compactly represents many equivalent programs in an e-graph and delays commitment until extraction selects a lowest-cost program. Making EqSat effective, therefore,…

Test-time scaling can improve model performance by aggregating stochastic reasoning trajectories. However, achieving sample-efficient test-time self-consistency under a limited budget remains an open challenge. We introduce PETS (Principled…

The increasing integration of distributed energy resources (DERs), variable renewable energy sources, and emerging technologies presents new challenges for transmission system expansion planning (TSEP). Traditional snapshot-based and…

Foundation models have revolutionized general-purpose problem-solving, offering rapid task adaptation through pretraining, meta-training, and finetuning. Recent crucial advances in these paradigms reveal the importance of challenging task…

Test-time training (TTT) adapts language models through gradient-based updates at inference. But is adaptation the right strategy? We study compute-optimal test-time strategies for verifiable execution-grounded (VEG) tasks, domains like GPU…

Deep learning inference is increasingly run at the edge. As the programming and system stack support becomes mature, it enables acceleration opportunities within a mobile system, where the system performance envelope is scaled up with a…

The sequential nature of modern LLMs makes them expensive and slow, and speculative sampling has proven to be an effective solution to this problem. Methods like EAGLE perform autoregression at the feature level, reusing top-layer features…