Related papers: Adaptive Blockwise Search: Inference-Time Alignmen…

Training autoregressive models to better predict under the test metric, instead of maximizing the likelihood, has been reported to be beneficial in several use cases but brings additional complications, which prevent wider adoption. In this…

The advancements in large language models (LLMs) have propelled the improvement of video understanding tasks by incorporating LLMs with visual models. However, most existing LLM-based models (e.g., VideoLLaMA, VideoChat) are constrained to…

Financial decision-making requires processing vast amounts of real-time information while understanding their complex temporal relationships. While traditional search engines excel at providing real-time information access, they often…

Multimodal Large Language Models (MLLMs) incur significant computational cost from processing numerous vision tokens through all LLM layers. Prior pruning methods operate either before the LLM, limiting generality due to diverse…

Large Language Models (LLMs) struggle with accuracy, domain-specific reasoning, and interpretability in vertical domains. Traditional preference alignment methods like Reinforcement Learning from Human Feedback (RLHF) and Direct Preference…

Large language models (LLMs) have enabled the creation of multi-modal LLMs that exhibit strong comprehension of visual data such as images and videos. However, these models usually rely on extensive visual tokens from visual encoders,…

Actively inferring user preferences, for example by asking good questions, is important for any human-facing decision-making system. Active inference allows such systems to adapt and personalize themselves to nuanced individual preferences.…

As Large Language Models (LLMs) have made significant advancements across various tasks, such as question answering, translation, text summarization, and dialogue systems, the need for accuracy in information becomes crucial, especially for…

Time series modeling holds significant importance in many real-world applications and has been extensively studied. While pre-trained foundation models have made impressive strides in the fields of natural language processing (NLP) and…

In-Context Learning (ICL) enables Large Language Models (LLMs) to perform new tasks by conditioning on prompts with relevant information. Retrieval-Augmented Generation (RAG) enhances ICL by incorporating retrieved documents into the LLM's…

Breaking down a problem into intermediate steps has demonstrated impressive performance in Large Language Model (LLM) reasoning. However, the growth of the reasoning chain introduces uncertainty and error accumulation, making it challenging…

Large Language Models (LLMs) demonstrate exceptional reasoning abilities, enabling strong generalization across diverse tasks such as commonsense reasoning and instruction following. However, as LLMs scale, inference costs become…

Backtracking line search is foundational in numerical optimization. The basic idea is to adjust the step-size of an algorithm by a constant factor until some chosen criterion (e.g. Armijo, Descent Lemma) is satisfied. We propose a novel way…

With the breakthroughs in large language models (LLMs), query generation techniques that expand documents and queries with related terms are becoming increasingly popular in the information retrieval field. Such techniques have been shown…

Existing research on large language models (LLMs) shows that they can solve information extraction tasks through multi-step planning. However, their extraction behavior on complex sentences and tasks is unstable, emerging issues such as…

Due to the prevalence of large language models (LLMs), key-value (KV) cache reduction for LLM inference has received remarkable attention. Among numerous works that have been proposed in recent years, layer-wise token pruning approaches,…

Adaptive stochastic gradient methods such as AdaGrad have gained popularity in particular for training deep neural networks. The most commonly used and studied variant maintains a diagonal matrix approximation to second order information by…

Aiming at solving large-scale learning problems, this paper studies distributed optimization methods based on the alternating direction method of multipliers (ADMM). By formulating the learning problem as a consensus problem, the ADMM can…

Decoding from large language models (LLMs) typically relies on fixed sampling hyperparameters (e.g., temperature, top-p), despite substantial variation in task difficulty and uncertainty across prompts and individual decoding steps. We…

Inference-time techniques, such as repeated sampling or iterative revisions, are emerging as powerful ways to enhance large-language models (LLMs) at test time. However, best practices for developing systems that combine these techniques…