相关论文: TwiSTAR:Think Fast, Think Slow, Then Act,Generativ…

Generative Recommendation (GR) has emerged as a transformative paradigm that reformulates the traditional cascade ranking system into a sequence-to-item generation task, facilitated by the use of discrete Semantic IDs (SIDs). However,…

There emerges a promising trend of using large language models (LLMs) to generate code-like plans for complex inference tasks such as visual reasoning. This paradigm, known as LLM-based planning, provides flexibility in problem solving and…

Standard chain-of-thought reasoning generates a solution in a single forward pass, committing irrevocably to each token and lacking a mechanism to recover from early errors. We introduce Inference-Time Rethinking, a generative framework…

Recent advances in large language models (LLMs) have demonstrated the power of reasoning through self-generated chains of thought. Multiple reasoning agents can collaborate to raise joint reasoning quality above individual outcomes.…

We propose Re-FORC, an adaptive reward prediction method that, given a context, enables prediction of the expected future rewards as a function of the number of future thinking tokens. Re-FORC trains a lightweight adapter on reasoning…

Large language models (LLMs) have demonstrated strong reasoning abilities in mathematical tasks, often enhanced through reinforcement learning (RL). However, RL-trained models frequently produce unnecessarily long reasoning traces -- even…

Latent reasoning represents a new development in Transformer language models that has shown potential in compressing reasoning lengths compared to chain-of-thought reasoning. By directly passing the information-rich previous final latent…

In Semantic-ID (SID) based generative recommendation, each item is represented as a sequence of discrete codes, and an autoregressive model is trained to generate the SID sequence of the next item; top-K performance is then measured by…

In cold-start scenarios, the scarcity of collaborative signals for new items exacerbates the Matthew effect, which undermines platform diversity and remains a persistent challenge in real-world recommender systems. Existing methods…

Large Language Models (LLMs) often falter in complex reasoning tasks due to their static, parametric knowledge, leading to hallucinations and poor performance in specialized domains like mathematics. This work explores a fundamental…

Achieving human-level intelligence requires refining cognitive distinctions between System 1 and System 2 thinking. While contemporary AI, driven by large language models, demonstrates human-like traits, it falls short of genuine cognition.…

Recent advances in Large Language Models (LLMs) demonstrate that chain-of-thought prompting and deep reasoning substantially enhance performance on complex tasks, and multi-agent systems can further improve accuracy by enabling model…

Generative models powered by Large Language Models (LLMs) are emerging as a unified solution for powering both recommendation and search tasks. A key design choice in these models is how to represent items, traditionally through unique…

Sequential recommendation increasingly employs latent multi-step reasoning to enhance test-time computation. Despite empirical gains, existing approaches largely drive intermediate reasoning states via target-dominant objectives without…

Sequential recommender systems have become increasingly important in real-world applications that model user behavior sequences to predict their preferences. However, existing sequential recommendation methods predominantly rely on…

Recently, large reasoning models demonstrate exceptional performance on various tasks. However, reasoning models always consume excessive tokens even for simple queries, leading to resource waste and prolonged user latency. To address this…

Generative conversational interfaces powered by large language models (LLMs) typically stream output token-by-token at a rate determined by computational budget, often neglecting actual human reading speeds and the cognitive load associated…

Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to access external knowledge sources, but the effectiveness of RAG relies on the coordination between the retriever and the generator. Since these components are…

This paper introduces lateral thinking to implement System-2 reasoning capabilities in AI systems, focusing on anticipatory and causal reasoning under uncertainty. We present a framework for systematic generation and modeling of lateral…

The Stop-Think-AutoRegress Language Diffusion Model (STAR-LDM) integrates latent diffusion planning with autoregressive generation. Unlike conventional autoregressive language models limited to token-by-token decisions, STAR-LDM…