相关论文: A Preliminary Agentic Framework for Matrix Deflati…

Large Language Models (LLMs) excel at various tasks, including solving math word problems (MWPs), but struggle with real-world problems containing irrelevant information. To address this, we propose a prompting framework that generates…

Can large language models (LLMs) generate continuous numerical features that improve reinforcement learning (RL) trading agents? We build a modular pipeline where a frozen LLM serves as a stateless feature extractor, transforming…

Large language models (LLMs) significantly enhance the performance of various applications, but they are computationally intensive and energy-demanding. This makes it challenging to deploy them on devices with limited resources, such as…

Large Language Models (LLMs) have shown remarkable performance in completing various tasks. However, solving complex problems often requires the coordination of multiple agents, raising a fundamental question: how to effectively select and…

We present Stable-Layers, a reinforcement learning framework that eliminates the need for paired supervision by fine-tuning a pretrained layer decomposition model using only feedback from a vision-language model (VLM). Starting from…

The rise of Agentic applications and automation in the Voice AI industry has led to an increased reliance on Large Language Models (LLMs) to navigate graph-based logic workflows composed of nodes and edges. However, existing methods face…

We study the Sparse Plus Low-Rank decomposition problem (SLR), which is the problem of decomposing a corrupted data matrix into a sparse matrix of perturbations plus a low-rank matrix containing the ground truth. SLR is a fundamental…

Foundation models face growing compute and memory bottlenecks, hindering deployment on resource-limited platforms. While compression techniques such as pruning and quantization are widely used, most rely on uniform heuristics that ignore…

Recent large language models (LLMs) employ billions of parameters to enable broad problem-solving capabilities. Such language models also tend to be memory-bound because of the dominance of matrix-vector and matrix-matrix multiplications…

Multi-modal large language models (MLLMs) advance vision language understanding but face inherent limitations in long-video tasks due to bounded perception context budgets. Existing agentic methods mitigate this via rule-based…

This paper studies the deflation algorithm when applied to estimate a low-rank symmetric spike contained in a large tensor corrupted by additive Gaussian noise. Specifically, we provide a precise characterization of the large-dimensional…

Large Language Models (LLMs) are increasingly explored for legal argument generation, yet they pose significant risks of manipulation through hallucination and ungrounded persuasion, and often fail to utilize provided factual bases…

We introduce and compare new compression approaches to obtain regularized solutions of large linear systems which are commonly encountered in large scale inverse problems. We first describe how to approximate matrix vector operations with a…

Image classification has traditionally relied on parameter-intensive model training, requiring large-scale annotated datasets and extensive fine tuning to achieve competitive performance. While recent vision language models (VLMs) alleviate…

Large language models (LLMs) have recently been used to empower autonomous agents in engineering, significantly improving automation and efficiency in labor-intensive workflows. However, their potential remains underexplored in structural…

Large Language Models (LLMs) are very demanding in terms of their computational resources. Low-rank decompositions of LLM weights, e.g. via Singular Value Decomposition (SVD), is a promising approach for LLM compression, but presents…

Large language models (LLMs) are increasingly deployed as agents, expected to decompose goals, invoke tools, and verify results in dynamic environments. Realizing these capabilities requires access to agentic data-structured interaction…

Extending the capabilities of Large Language Models (LLMs) with functions or tools for environment interaction has led to the emergence of the agent paradigm. In industry, training an LLM is not always feasible because of the scarcity of…

High-dimensional data remains a pervasive challenge in machine learning, often undermining model interpretability and computational efficiency. While Large Language Models (LLMs) have shown promise for dimensionality reduction through…

Task planning for robotic manipulation with large language models (LLMs) is an emerging area. Prior approaches rely on specialized models, fine tuning, or prompt tuning, and often operate in an open loop manner without robust environmental…