Related papers: FlashEvaluator: Expanding Search Space with Parall…
In recent years, there has been significant progress in the development of text-to-image generative models. Evaluating the quality of the generative models is one essential step in the development process. Unfortunately, the evaluation…
Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks when equipped with external tools. However, current frameworks predominantly rely on sequential processing, leading to inefficient execution…
In a multi-stage recommendation system, reranking plays a crucial role in modeling intra-list correlations among items. A key challenge lies in exploring optimal sequences within the combinatorial space of permutations. Recent research…
Neural document ranking approaches, specifically transformer models, have achieved impressive gains in ranking performance. However, query processing using such over-parameterized models is both resource and time intensive. In this paper,…
Retrieval-Augmented Generation (RAG) couples a retriever with a large language model (LLM) to ground generated responses in external evidence. While this framework enhances factuality and domain adaptability, it faces a key bottleneck:…
Most problems in search-based software engineering involve balancing conflicting objectives. Prior approaches to this task have required a large number of evaluations- making them very slow to execute and very hard to comprehend. To solve…
We present GraphTensor, a comprehensive open-source framework that supports efficient parallel neural network processing on large graphs. GraphTensor offers a set of easy-to-use programming primitives that appreciate both graph and neural…
Recently introduced EASE algorithm presents a simple and elegant way, how to solve the top-N recommendation task. In this paper, we introduce Neural EASE to further improve the performance of this algorithm by incorporating techniques for…
Parallel search algorithms have been shown to improve planning speed by harnessing the multithreading capability of modern processors. One such algorithm PA*SE achieves this by parallelizing state expansions, whereas another algorithm…
Generative reward models with parallel sampling have enabled effective test-time scaling for reasoning tasks. Current approaches employ pointwise scoring of individual solutions or pairwise comparisons. However, pointwise methods…
The promotion of large-scale applications of reinforcement learning (RL) requires efficient training computation. While existing parallel RL frameworks encompass a variety of RL algorithms and parallelization techniques, the excessively…
This paper introduces a novel Deep Researcher architecture designed to generate detailed research reports on complex PhD level topics by addressing the inherent limitations of the Parallel Scaling paradigm. Our system utilizes two key…
Modern search systems play a crucial role in facilitating information acquisition. Traditional search engines typically rely on a cascaded architecture, where results are retrieved through recall, pre-ranking, and ranking stages. The…
In the combinatorial recommender systems, multiple items are fed to the user at one time in the result page, where the correlations among the items have impact on the user behavior. In this work, we model the combinatorial recommendation as…
Transformer-based models have made tremendous impacts in natural language generation. However the inference speed is a bottleneck due to large model size and intensive computing involved in auto-regressive decoding process. We develop…
In multi-stage recommender systems, reranking optimizes overall utility by capturing intra-list contextual dependencies, yet its central challenge lies in exploring optimal sequences within an exponentially large permutation space. Recent…
Recent advancements in visual generative models have enabled high-quality image and video generation, opening diverse applications. However, evaluating these models often demands sampling hundreds or thousands of images or videos, making…
There are two halves to RL systems: experience collection time and policy learning time. For a large number of samples in rollouts, experience collection time is the major bottleneck. Thus, it is necessary to speed up the rollout generation…
Speculative decoding accelerates generation by drafting candidates and verifying them in parallel, yet state-of-the-art drafters (e.g., EAGLE) still require N sequential passes to propose N tokens. We present FastEagle, a non-autoregressive…
Agentic AI systems execute a sequence of actions, such as reasoning steps or tool calls, in response to a user prompt. To evaluate the success of their trajectories, researchers have developed verifiers, such as LLM judges and…