Related papers: Evolutionary Guided Decoding: Iterative Value Refi…

While language models have shown remarkable performance across diverse tasks, they still encounter challenges in complex reasoning scenarios. Recent research suggests that language models trained on linearized search traces toward…

Large language models (LLMs) exhibit impressive natural language capabilities but suffer from hallucination -- generating content ungrounded in the realities of training data. Recent work has focused on decoding techniques to improve…

Discrete diffusion models have emerged as a promising direction for vision-language tasks, offering bidirectional context modeling and theoretical parallelization. However, their practical application is severely hindered by a…

Large Language Models (LLMs) have demonstrated remarkable versatility across various domains. To further advance LLMs, we propose 'SELF' (Self-Evolution with Language Feedback), a novel approach that enables LLMs to self-improve through…

Large language models (LLMs) have demonstrated remarkable proficiency in machine translation (MT), even without specific training on the languages in question. However, translating rare words in low-resource or domain-specific contexts…

Iterative retrieval-augmented generation (RAG) enables large language models to answer complex multi-hop questions, but each additional loop increases latency, costs, and the risk of introducing distracting evidence, motivating the need for…

Publicly available, large pretrained LanguageModels (LMs) generate text with remarkable quality, but only sequentially from left to right. As a result, they are not immediately applicable to generation tasks that break the unidirectional…

Designing effective control policies for autonomous systems remains a fundamental challenge, traditionally addressed through reinforcement learning or manual engineering. While reinforcement learning has achieved remarkable success, it…

Reinforcement learning (RL) has been effective for post-training autoregressive (AR) language models, but extending these methods to diffusion language models (DLMs) is challenging due to intractable sequence-level likelihoods. Existing…

The evolution of Large Language Model (LLM) reasoning is bottlenecked by the scarcity of high-quality process data. While self-alignment via endogenous rewards offers a solution, mining valid supervision faces three challenges: (1) Label…

Reinforcement Learning from Human Feedback (RLHF), using algorithms like Proximal Policy Optimization (PPO), aligns Large Language Models (LLMs) with human values but is costly and unstable. Alternatives have been proposed to replace PPO or…

Large Language Models (LLMs) are nowadays expected to generate content aligned with human preferences. Current work focuses on alignment at model training time, through techniques such as Reinforcement Learning with Human Feedback (RLHF).…

We introduce iterative retrieval, a novel framework that empowers retrievers to make iterative decisions through policy optimization. Finding an optimal portfolio of retrieved items is a combinatorial optimization problem, generally…

Large vision-language models (VLMs) fine-tuned on specialized visual instruction-following data have exhibited impressive language reasoning capabilities across various scenarios. However, this fine-tuning paradigm may not be able to…

Large Language Models (LLMs) have achieved significant advances in reasoning tasks. A key approach is tree-based search with verifiers, which expand candidate reasoning paths and use reward models to guide pruning and selection. Although…

Denoising-based generative models, particularly diffusion and flow matching algorithms, have achieved remarkable success. However, aligning their output distributions with complex downstream objectives, such as human preferences,…

Generating high-quality code that solves complex programming tasks is challenging, especially with current decoder-based models that produce highly stochastic outputs. In code generation, even minor errors can easily break the entire…

The capabilities of Large Language Models (LLMs) in code generation have been extensively studied, particularly for implementing target functionalities from natural-language descriptions. Alternatively, input-output (I/O) examples provide…

As Large Language Models (LLMs) achieve remarkable breakthroughs, aligning their values with humans has become imperative for their responsible development and customized applications. However, there still lack evaluations of LLMs values…

In recent times, Vision-Language Models (VLMs) have been trained under two predominant paradigms. Generative training has enabled Multimodal Large Language Models (MLLMs) to tackle various complex tasks, yet issues such as hallucinations…