Related papers: Satori-SWE: Evolutionary Test-Time Scaling for Sam…

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…

The growing emotional stress in modern society has increased the demand for Emotional Support Conversations (ESC). While Large Language Models (LLMs) show promise for ESC, they face two key challenges: (1) low strategy selection accuracy,…

Large language models (LLMs) can generate syntactically valid optimization programs, yet often struggle to reliably choose an effective modeling strategy, leading to incorrect formulations and inefficient solver behavior. We propose SAGE, a…

The rapid growth of dataset scales has been a key driver in advancing deep learning research. However, as dataset scale increases, the training process becomes increasingly inefficient due to the presence of low-value samples, including…

Existing fine-tuning methods either tune all parameters of the pre-trained model (full fine-tuning), which is not efficient, or only tune the last linear layer (linear probing), which suffers a significant accuracy drop compared to the full…

We introduce EvoLib, a test-time learning framework that enables large language models to accumulate, reuse, and evolve knowledge across problem instances without parameter updates or external supervision. Instead of adapting model…

Large language models (LLMs) have achieved impressive results on multi-step mathematical reasoning, yet at the cost of high computational overhead. This challenge is particularly acute for test-time scaling methods such as parallel…

Existing data generation methods suffer from exploration limits, embodiment gaps, and low signal-to-noise ratios, leading to performance degradation during self-iteration. To address these challenges, we propose Seed2Scale, a self-evolving…

Self-Supervised Learning (SSL) models have demonstrated exceptional performance in various speech tasks, particularly in low-resource and multilingual domains. Recent works show that fusing diverse SSL models could achieve superior…

The recent advancements of Small Language Models (SLMs) have opened new possibilities for efficient code generation. SLMs offer lightweight and cost-effective alternatives to Large Language Models (LLMs), making them attractive for use in…

Frontier Large language models (LLMs) like ChatGPT and Gemini can decipher cryptic compiler errors for novice programmers, but their computational scale, cost, and tendency to over-assist make them problematic for widespread pedagogical…

Large Language Models (LLMs) have shown strong capability in diverse software engineering tasks. However, feature-driven development, a highly prevalent real-world task that involves developing new functionalities for large, existing…

Time series classification is a fundamental machine learning task with broad real-world applications. Although many deep learning methods have proven effective in learning time-series data for classification, they were originally developed…

Benchmark datasets are crucial for evaluating approaches to scheduling or dispatching in the semiconductor industry during the development and deployment phases. However, commonly used benchmark datasets like the Minifab or SMT2020 lack the…

Steering has emerged as a promising approach in controlling large language models (LLMs) without modifying model parameters. However, most existing steering methods rely on large-scale datasets to learn clear behavioral information, which…

Test-Time Scaling enhances the reasoning capabilities of Large Language Models by allocating additional inference compute to broaden the exploration of the solution space. However, existing search strategies typically treat rollouts as…

Evaluating software engineering capabilities has become a core component of modern large language models (LLMs); however, the key bottleneck hindering further scaling lies not in the scarcity of high-quality solutions, but in the lack of…

Software engineers operating in complex and dynamic environments must continuously adapt to evolving requirements, learn iteratively from experience, and reconsider their approaches based on new insights. However, current large language…

Scaling the test-time compute of large language models has demonstrated impressive performance on reasoning benchmarks. However, existing evaluations of test-time scaling make the strong assumption that a reasoning system should always give…

Large Language Models have seen increasing use in various software development tasks, especially in code generation. The most advanced recent methods attempt to incorporate feedback from code execution into prompts to help guide LLMs in…