Related papers: REVISION:Reflective Intent Mining and Online Reaso…
Evaluating retrieval-ranking systems is crucial for developing high-performing models. While online A/B testing is the gold standard, its high cost and risks to user experience require effective offline methods. However, relying on…
Driven by advances in Large Language Models (LLMs), integrating them into recommendation tasks has gained interest due to their strong semantic understanding and prompt flexibility. Prior work encoded user-item interactions or metadata into…
Recommendation systems, which assist users in discovering their preferred items among numerous options, have served billions of users across various online platforms. Intuitively, users' interactions with items are highly driven by their…
For ambiguous queries, conventional retrieval systems are bound by two conflicting goals. On the one hand, they should diversify and strive to present results for as many query intents as possible. On the other hand, they should provide…
Reasoning-augmented vision language models (VLMs) generate explicit chains of thought that promise greater capability and transparency but also introduce new failure modes: models may reach correct answers via visually unfaithful…
Multimodal Large Language Models (MLLMs) have achieved remarkable progress in multimodal reasoning. However, they often excessively rely on textual information during the later stages of inference, neglecting the crucial integration of…
Offline reinforcement learning (RL) is crucial when online exploration is costly or unsafe but often struggles with high epistemic uncertainty due to limited data. Existing methods rely on fixed conservative policies, restricting adaptivity…
Proactive intent prediction is a critical capability in modern e-commerce chatbots, enabling "zero-query" recommendations by anticipating user needs from behavioral and contextual signals. However, existing industrial systems face two…
Industrial recommender systems face two fundamental limitations under the log-driven paradigm: (1) knowledge poverty in ID-based item representations that causes brittle interest modeling under data sparsity, and (2) systemic blindness to…
Finetuning Large Vision-Language Models with reinforcement learning has emerged as a promising approach to enhance their capability in object-level grounding. However, existing methods, mainly based on GRPO, assign rewards at the response…
Composed Video Retrieval (CoVR) aims to find a target video given a reference video and a textual modification. Prior work assumes the modification text fully specifies the visual changes, overlooking after-effects and implicit consequences…
Recent advances in large multimodal models have leveraged image-based tools with reinforcement learning to tackle visual problems. However, existing open-source approaches often exhibit monotonous reasoning patterns and allow only a limited…
Understanding text-rich videos requires reading small, transient textual cues that often demand repeated inspection. Yet most video QA models rely on single-pass perception over fixed frames, leading to hallucinations and failures on…
Understanding user intent is essential for effective planning in conversational assistants, particularly those powered by large language models (LLMs) coordinating multiple agents. However, real-world dialogues are often ambiguous,…
The rapid rise of large language models has shifted user search behavior from discrete keywords to natural-language, multi-constraint queries--a shift existing e-commerce search architectures struggle to accommodate. Users face a dilemma:…
With the recent surge of NLP technologies in the financial domain, banks and other financial entities have adopted virtual agents (VA) to assist customers. A challenging problem for VAs in this domain is determining a user's reason or…
Traditional machine-learned ranking systems for web search are often trained to capture stationary relevance of documents to queries, which has limited ability to track non-stationary user intention in a timely manner. In recency search,…
User comments on online programming platforms such as Stack Overflow play a vital role in maintaining the correctness and relevance of shared code examples. However, the majority of comments express gratitude or clarification, while only a…
Sequential recommendation systems aim to capture users' evolving preferences from their interaction histories. Recent reasoningenhanced methods have shown promise by introducing deliberate, chain-of-thought-like processes with intermediate…
Text-to-Image (T2I) models and Unified Multimodal Models (UMMs) have achieved remarkable progress in visual generation. However, their reliance on a single-pass generation paradigm limits their ability to handle complex prompts requiring…