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

We present Entropy Adaptive Decoding (EAD), a novel approach for efficient language model inference that dynamically switches between different-sized models based on prediction uncertainty. By monitoring rolling entropy in model logit…

Unconditionally stable time stepping schemes are useful and often practically necessary for advancing parabolic operators in multi-scale systems. However, serious accuracy problems may emerge when taking time steps that far exceed the…

This paper presents a simple, effective, and cost-efficient strategy to improve LLM performance by scaling test-time compute. Our strategy builds upon the repeated-sampling-then-voting framework, with a novel twist: incorporating multiple…

Gradient Boosted Decision Trees (GBDTs) are widely used for building ranking and relevance models in search and recommendation. Considerations such as latency and interpretability dictate the use of as few features as possible to train…

PET requires accurate, precise, and efficient scatter correction techniques. Conventional scatter estimation typically relies on tail-fitted single-scatter simulation (SSS) strategy. However, the accuracy of tail-fitted SSS is limited, for…

Recently, large-scale transformer-based models have been proven to be effective over various tasks across many domains. Nevertheless, applying them in industrial production requires tedious and heavy works to reduce inference costs. To fill…

Time series forecasting (TSF) is critical across domains such as finance, meteorology, and energy. While extending the lookback window theoretically provides richer historical context, in practice, it often introduces irrelevant noise and…

Large Language Models (LLMs) and agent-based systems often struggle with compositional generalization due to a data bottleneck in which complex skill combinations follow a long-tailed, power-law distribution, limiting both…

Test-time adaptation (TTA) methods, which generally rely on the model's predictions (e.g., entropy minimization) to adapt the source pretrained model to the unlabeled target domain, suffer from noisy signals originating from 1) incorrect or…

The paper presents an approach for building consistent and applicable clinical decision support systems (CDSSs) using a data-driven predictive model aimed at resolving the problem of low applicability and scalability of CDSSs in real-world…

Autoregressive (AR) architectures have achieved significant successes in LLMs, inspiring explorations for video generation. In LLMs, top-p/top-k sampling strategies work exceptionally well: language tokens have high semantic density and low…

Current end-to-end autoregressive TTS systems (e.g. Tacotron 2) have outperformed traditional parallel approaches on the quality of synthesized speech. However, they introduce new problems at the same time. Due to the autoregressive nature,…

Agent harnesses increasingly determine the performance of language-model systems by deciding how models call tools, receive feedback, verify intermediate states, store memory, and revise solutions. Yet current test-time scaling analyses…

Graph Neural Networks deliver strong classification results but often suffer from poor calibration performance, leading to overconfidence or underconfidence. This is particularly problematic in high stakes applications where accurate…

A fundamental problem in multi-task learning (MTL) is identifying groups of tasks that should be learned together. Since training MTL models for all possible combinations of tasks is prohibitively expensive for large task sets, a crucial…

Test-time scaling (TTS) has gained widespread attention for enhancing LLM reasoning. Existing approaches such as Best-of-N and majority voting are limited as their performance depends on the quality of candidate responses, making them…

Test-time adaptation (TTA) seeks to tackle potential distribution shifts between training and testing data by adapting a given model w.r.t. any testing sample. This task is particularly important for deep models when the test environment…

The task of Text-to-SQL enables anyone to retrieve information from SQL databases using natural language. While this task has made substantial progress, the two primary evaluation metrics - Execution Accuracy (EXE) and Exact Set Matching…

In safety-critical systems, timing accuracy is the key to achieving precise I/O control. To meet such strict timing requirements, dedicated hardware assistance has recently been investigated and developed. However, these solutions are often…

Small Vision-Language Models (VLMs) provide a computationally efficient alternative to larger models, at the cost of weaker generalization abilities and downstream task performance. These shortcomings could be addressed by test-time scaling…