Related papers: RTTC: Reward-Guided Collaborative Test-Time Comput…

Large reasoning models (LRMs) have achieved strong performance enhancement through scaling test time computation, but due to the inherent limitations of the underlying language models, they still have shortcomings in tasks that require…

Deep learning models have demonstrated exceptional performance across a wide range of computer vision tasks. However, their performance often degrades significantly when faced with distribution shifts, such as domain or dataset changes.…

We propose a novel LLM-based framework for reasoning in discrete, game-theoretic tasks, illustrated with \emph{Tic-Tac-Toe}. The method integrates in-context learning with entropy-guided chain-of-thought (CoT) reasoning and adaptive context…

The objective of this work is to improve the accuracy of building demand forecasting. This is a more challenging task than grid level forecasting. For the said purpose, we develop a new technique called recurrent transform learning (RTL).…

Recently, the number of off-the-shelf Large Language Models (LLMs) has exploded with many open-source options. This creates a diverse landscape regarding both serving options (e.g., inference on local hardware vs remote LLM APIs) and model…

Scaling test-time compute has emerged as a powerful mechanism for enhancing Large Language Model (LLM) performance. However, standard post-training paradigms, Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), optimize the…

The scaling of inference computation has unlocked the potential of long-context large language models (LLMs) across diverse settings. For knowledge-intensive tasks, the increased compute is often allocated to incorporate more external…

Test-time compute scaling, the practice of spending extra computation during inference via repeated sampling, search, or extended reasoning, has become a powerful lever for improving large language model performance. Yet deploying these…

Retrieval-Augmented Generation (RAG) significantly improves the performance of Large Language Models (LLMs) on knowledge-intensive tasks. However, varying response quality across LLMs under RAG necessitates intelligent routing mechanisms,…

Test-time scaling (TTS) has enhanced the performance of Reasoning Models (RMs) on various tasks such as math and coding, yet its efficacy in machine translation (MT) remains underexplored. This paper investigates whether increased…

While large language models (LLMs) have demonstrated remarkable reasoning capabilities, they are not without their flaws and inaccuracies. Recent studies have introduced various methods to mitigate these limitations. Temporal reasoning…

Test-time scaling (TTS) improves large language models (LLMs) by allocating additional compute at inference time. In practice, TTS is often achieved through parallel scaling: generating multiple candidate responses and selecting the best…

Driven by the rapid growth of machine learning, recent advances in game artificial intelligence (AI) have significantly impacted productivity across various gaming genres. Reward design plays a pivotal role in training game AI models,…

The Retrieval Question Answering (ReQA) task employs the retrieval-augmented framework, composed of a retriever and generator. The generator formulates the answer based on the documents retrieved by the retriever. Incorporating Large…

Scaling training compute, measured in FLOPs, has long been shown to improve the accuracy of large language models, yet training remains resource-intensive. Prior work shows that increasing test-time compute (TTC)-for example through…

Understanding real-world videos with complex semantics and long temporal dependencies remains a fundamental challenge in computer vision. Recent progress in multimodal large language models (MLLMs) has demonstrated strong capabilities in…

Retrieval-augmented generation (RAG) enhances the text generation capabilities of large language models (LLMs) by integrating external knowledge and up-to-date information. However, traditional RAG systems are limited by static workflows…

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by pulling in external material, document, code, manuals, from vast and ever-growing corpora, to effectively answer user queries. The effectiveness of RAG depends…

Despite significant advances in Large Reasoning Models (LRMs) driven by reinforcement learning with verifiable rewards (RLVR), this paradigm is fundamentally limited in specialized or novel domains where such supervision is prohibitively…

Human reasoning is shaped by resource rationality -- optimizing performance under constraints. Recently, inference-time scaling has emerged as a powerful paradigm to improve the reasoning performance of Large Language Models by expanding…