Related papers: Taming Imperfect Process Verifiers: A Sampling Per…

TextGrad is a novel approach to text-based automatic differentiation that enables composite AI systems to perform optimization without explicit numerical equations. However, it currently lacks self-verification mechanisms that ensure…

Bug reproduction is critical in the software debugging and repair process, yet the majority of bugs in open-source and industrial settings lack executable tests to reproduce them at the time they are reported, making diagnosis and…

Software Testing is a process to identify the quality and reliability of software, which can be achieved through the help of proper test data. However, doing this manually is a difficult task due to the presence of number of predicate nodes…

Counterfactual learning has become promising for understanding and modeling causality in complex and dynamic systems. This paper presents a novel method for counterfactual learning in the context of multivariate time series analysis and…

Scaling test-time compute has emerged as a key strategy for enhancing the reasoning capabilities of large language models (LLMs), particularly in tasks like mathematical problem-solving. A traditional approach, Self-Consistency (SC),…

Large Language Models (LLMs) show promise in code generation tasks. However, their code-writing abilities are often limited in scope: while they can successfully implement simple functions, they struggle with more complex tasks. A…

Recent studies increasingly explore Large Language Models (LLMs) as a new paradigm for recommendation systems due to their scalability and world knowledge. However, existing work has three key limitations: (1) most efforts focus on…

Large Language Models (LLMs) exhibit impressive capabilities but require careful alignment with human preferences. Traditional training-time methods finetune LLMs using human preference datasets but incur significant training costs and…

There have been wide spread claims in the literature about the emergent reasoning capabilities of Pretrained Large Language Models. However, recent studies, have found that their ability to plan remains questionable. Through our experiments…

We introduce Generative Universal Verifier, a novel concept and plugin designed for next-generation multimodal reasoning in vision-language models and unified multimodal models, providing the fundamental capability of reflection and…

Speculative decoding is a promising approach for accelerating large language models. The primary idea is to use a lightweight draft model to speculate the output of the target model for multiple subsequent timesteps, and then verify them in…

Generative retrieval seeks to replace traditional search index data structures with a single large-scale neural network, offering the potential for improved efficiency and seamless integration with generative large language models. As an…

Despite the crucial importance of accelerating text generation in large language models (LLMs) for efficiently producing content, the sequential nature of this process often leads to high inference latency, posing challenges for real-time…

The proliferation of deepfake faces poses huge potential negative impacts on our daily lives. Despite substantial advancements in deepfake detection over these years, the generalizability of existing methods against forgeries from unseen…

There has been a growing excitement that implicit graph generative models could be used to design or discover new molecules for medicine or material design. Because these molecules have not been discovered, they naturally lie in unexplored…

As large language models have evolved, it has become crucial to distinguish between process supervision and outcome supervision -- two key reinforcement learning approaches to complex reasoning tasks. While process supervision offers…

Large language models have achieved high performance on various question answering (QA) benchmarks, but the explainability of their output remains elusive. Structured explanations, called entailment trees, were recently suggested as a way…

Generative modeling builds on and substantially advances the classical idea of simulating synthetic data from observed samples. This paper shows that this principle is not only natural but also theoretically well-founded for bootstrap…

Autoregression in large language models (LLMs) has shown impressive scalability by unifying all language tasks into the next token prediction paradigm. Recently, there is a growing interest in extending this success to vision foundation…

Grounding large language models (LLMs) in external knowledge sources is a promising method for faithful prediction. While existing grounding approaches work well for simple queries, many real-world information needs require synthesizing…