Related papers: EGSS: Entropy-guided Stepwise Scaling for Reliable…
We introduce RapFlow-TTS, a rapid and high-fidelity TTS acoustic model that leverages velocity consistency constraints in flow matching (FM) training. Although ordinary differential equation (ODE)-based TTS generation achieves…
This study introduces an advanced transient stability assessment (TSA) method for power systems, addressing the challenges of sample class imbalance and data noise through a novel CatBoost algorithm framework. By implementing a Gradient…
Even well-designed software systems suffer from chronic performance degradation, also named "software aging", due to internal (e.g. software bugs) and external (e.g. resource exhaustion) impairments. These chronic problems often fly under…
While fully-supervised deep learning yields good models for urban scene semantic segmentation, these models struggle to generalize to new environments with different lighting or weather conditions for instance. In addition, producing the…
Generation expansion planning (GEP) is a prominent example of capacity expansion problems in operations research. Being generally NP-hard, GEP optimization models can become intractable when nonconvex dynamics, time-coupling constraints,…
This paper presents a novel procedure for energy management system (EMS) that can utilize the flexibility in transmission network in a practical way. With the proposed enhanced EMS procedure, the reliability benefits that are provided by…
Test-time reinforcement learning generates multiple candidate answers via repeated rollouts and performs online updates using pseudo-labels constructed by majority voting. To reduce overhead and improve exploration, prior work introduces…
Fact-checking real-world claims, particularly numerical claims, is inherently complex that require multistep reasoning and numerical reasoning for verifying diverse aspects of the claim. Although large language models (LLMs) including…
Recently, deep learning-based Text-to-Speech (TTS) systems have achieved high-quality speech synthesis results. Recurrent neural networks have become a standard modeling technique for sequential data in TTS systems and are widely used.…
Electromagnetic transient (EMT) simulation is a crucial tool for power system dynamic analysis because of its detailed component modeling and high simulation accuracy. However, it suffers from computational burdens for large power grids…
Similarity search, the task of identifying objects most similar to a given query object under a specific metric, has gathered significant attention due to its practical applications. However, the absence of coordinate information to…
Scaling laws for Large Language Models (LLMs) establish that model quality improves with computational scale, yet edge deployment imposes strict constraints on compute, memory, and power. Since General Matrix Multiplication (GEMM) accounts…
Large language model pretraining is compute-intensive, yet many tokens contribute marginally to learning, resulting in inefficiency. We introduce Efficient Selective Language Modeling (ESLM), a risk-aware algorithm that improves training…
Technical documents contain rich domain knowledge for automating downstream tasks such as system testing. While this paper focuses on Ethernet switch configuration manuals (ESCMs), we propose a general framework that can be adapted to…
We introduce AegisLLM, a cooperative multi-agent defense against adversarial attacks and information leakage. In AegisLLM, a structured workflow of autonomous agents - orchestrator, deflector, responder, and evaluator - collaborate to…
Test-Time Scaling (TTS) enhances the reasoning capabilities of large language models by allocating additional inference compute to explore the solution space. However, existing parallel TTS methods typically keep branches isolated during…
Language models are increasingly used in scientific discovery to generate hypotheses, propose candidate solutions, implement systems, and iteratively refine them. At the core of these trial-and-error loops lies evaluation: the process of…
Enabling agentic AI systems to adapt their problem-solving approaches based on post-training interactions remains a fundamental challenge. While systems that update and maintain a memory at inference time have been proposed, existing…
Real-world reinforcement learning often faces environment drift, but most existing methods rely on static entropy coefficients/target entropy, causing over-exploration during stable periods and under-exploration after drift, and leaving…
Automatic speech recognition (ASR) models are frequently exposed to data distribution shifts in many real-world scenarios, leading to erroneous predictions. To tackle this issue, an existing test-time adaptation (TTA) method has recently…