相关论文: Phase Locking Value revisited: teaching new tricks…

Proximal Policy Optimization (PPO) is central to aligning Large Language Models (LLMs) in reasoning tasks with verifiable rewards. However, standard token-level PPO struggles in this setting due to the instability of temporal credit…

Since sparse neural networks usually contain many zero weights, these unnecessary network connections can potentially be eliminated without degrading network performance. Therefore, well-designed sparse neural networks have the potential to…

Traditional logic programming relies on symbolic computation on the CPU, which can limit performance for large-scale inference tasks. Recent advances in GPU hardware enable high-throughput matrix operations, motivating a shift toward…

While Reinforcement Learning from Human Feedback (RLHF) significantly enhances the generation quality of Large Language Models (LLMs), recent studies have raised concerns regarding the complexity and instability associated with the Proximal…

Recent results in end-to-end automatic speech recognition have demonstrated the efficacy of pseudo-labeling for semi-supervised models trained both with Connectionist Temporal Classification (CTC) and Sequence-to-Sequence (seq2seq) losses.…

Incorporating external knowledge in large language models (LLMs) enhances their utility across diverse applications, but existing methods have trade-offs. Retrieval-Augmented Generation (RAG) fetches evidence via similarity search, but key…

With the rapid expansion of large language models (LLMs), the demand for memory and computational resources has grown significantly. Recent advances in LLM pruning aim to reduce the size and computational cost of these models. However,…

Reinforcement Learning with Verifiable Rewards (RLVR) significantly enhances the reasoning capability of Large Language Models (LLMs). Current RLVR approaches typically conduct training across all generated tokens, but neglect to explore…

We consider an $\ell_2$-regularized non-convex optimization problem for recovering signals from their noisy phaseless observations. We design and study the performance of a message passing algorithm that aims to solve this optimization…

We address the problem of phase retrieval (PR) from quantized measurements. The goal is to reconstruct a signal from quadratic measurements encoded with a finite precision, which is indeed the case in many practical applications. We develop…

Emerging real-time computer vision (CV) applications on wireless edge devices demand energy-efficient and privacy-preserving learning. Federated learning (FL) enables on-device training without raw data sharing, yet remains challenging in…

Dynamics and function of neuronal networks are determined by their synaptic connectivity. Current experimental methods to analyze synaptic network structure on the cellular level, however, cover only small fractions of functional neuronal…

Large language models (LLMs) have demonstrated remarkable performance, but their long-context reasoning remains constrained by the excessive memory required for the Key-Value (KV) cache. This makes KV cache compression a critical step…

Progressive Learning (PL) reduces pre-training computational overhead by gradually increasing model scale. While prior work has extensively explored depth expansion, width expansion remains significantly understudied, with the few existing…

Designing a module or mechanism that enables a network to maintain low parameters and FLOPs without sacrificing accuracy and throughput remains a challenge. To address this challenge and exploit the redundancy within feature map channels,…

Brain atrophy is an important biomarker for monitoring neurodegeneration and disease progression in conditions such as multiple sclerosis (MS). An accurate and robust quantitative measurement of brain volume change is paramount for…

Finding relevant and high-quality datasets to train machine learning models is a major bottleneck for practitioners. Furthermore, to address ambitious real-world use-cases there is usually the requirement that the data come labelled with…

This paper deals with the problem of inferring the signals and parameters that cause neural activity to occur. The ultimate challenge being to unveil brain's connectivity, here we focus on a microscopic vision of the problem, where single…

Large Language Models (LLMs) have recently improved mathematical reasoning through Reinforcement Learning with Verifiable Reward (RLVR). However, existing RLVR algorithms require large query budgets, making annotation costly. We investigate…

Post-training quantization (PTQ) is an effective technique for compressing large language models (LLMs). However, while uniform-precision quantization is computationally efficient, it often compromises model performance. To address this, we…