Related papers: Retrieval-GRPO: A Multi-Objective Reinforcement Le…

Generative retrieval introduces a groundbreaking paradigm to document retrieval by directly generating the identifier of a pertinent document in response to a specific query. This paradigm has demonstrated considerable benefits and…

Optimizing discrete diffusion model (DDM) with rewards remains a challenge: the non-autoregressive paradigm makes importance sampling intractable and rollout complex, puzzling reinforcement learning methods such as Group Relative Policy…

Generative speech enhancement offers a promising alternative to traditional discriminative methods by modeling the distribution of clean speech conditioned on noisy inputs. Post-training alignment via reinforcement learning (RL) effectively…

Reinforcement Learning with Human Feedback (RLHF) has been the dominant approach for improving the reasoning capabilities of Large Language Models (LLMs). Recently, Reinforcement Learning with Verifiable Rewards (RLVR) has simplified this…

When applying reinforcement learning--typically through GRPO--to large vision-language model reasoning struggles to effectively scale reasoning length or generates verbose outputs across all tasks with only marginal gains in accuracy. To…

Blind Face Restoration (BFR) encounters inherent challenges in exploring its large solution space, leading to common artifacts like missing details and identity ambiguity in the restored images. To tackle these challenges, we propose a…

In Taobao e-commerce visual search, user behavior analysis reveals a large proportion of no-click requests, suggesting diverse and implicit user intents. These intents are expressed in various forms and are difficult to mine and discover,…

Recent advances in large language models (LLMs) have shown that reasoning ability can be significantly enhanced through Reinforcement Learning with Verifiable Rewards (RLVR). Group Relative Policy Optimization (GRPO) has emerged as the de…

In the realm of e-commerce search, the significance of semantic matching cannot be overstated, as it directly impacts both user experience and company revenue. Along this line, query rewriting, serving as an important technique to bridge…

Text retrieval is a long-standing research topic on information seeking, where a system is required to return relevant information resources to user's queries in natural language. From classic retrieval methods to learning-based ranking…

Model-based reinforcement learning (RL) is considered to be a promising approach to reduce the sample complexity that hinders model-free RL. However, the theoretical understanding of such methods has been rather limited. This paper…

Large language models (LLMs) augmented with external tools are increasingly deployed as deep research agents that gather, reason over, and synthesize web information to answer complex queries. Although recent open-source systems achieve…

Search agents extend Large Language Models (LLMs) beyond static parametric knowledge by enabling access to up-to-date and long-tail information unavailable during pretraining. While reinforcement learning has been widely adopted for…

Dense retrieval has made significant advancements in information retrieval (IR) by achieving high levels of effectiveness while maintaining online efficiency during a single-pass retrieval process. However, the application of pseudo…

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective approach for improving the reasoning abilities of large language models (LLMs). The Group Relative Policy Optimization (GRPO) family has demonstrated strong…

In a number of information retrieval applications (e.g., patent search, literature review, due diligence, etc.), preventing false negatives is more important than preventing false positives. However, approaches designed to reduce review…

Despite considerable progress in neural relevance ranking techniques, search engines still struggle to process complex queries effectively - both in terms of precision and recall. Sparse and dense Pseudo-Relevance Feedback (PRF) approaches…

Reinforcement learning (RL) is pivotal for enhancing the reasoning capabilities of diffusion large language models (dLLMs). However, existing dLLM policy optimization methods suffer from two critical reliability bottlenecks: (1) reward…

Real-World Image Super-Resolution is one of the most challenging task in image restoration. However, existing methods struggle with an accurate understanding of degraded image content, leading to reconstructed results that are both…

Lexical and semantic matching capture different successful approaches to text retrieval and the fusion of their results has proven to be more effective and robust than either alone. Prior work performs hybrid retrieval by conducting lexical…