Related papers: S$^2$GR: Stepwise Semantic-Guided Reasoning in Lat…

Latent visual reasoning involves visual evidence more directly in multimodal reasoning by inserting continuous latent tokens before textual generation. However, the necessity of these latent tokens at inference remains ambiguous. We show…

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…

Structured representation of product information is a major bottleneck for the efficiency of e-commerce platforms, especially in second-hand ecommerce platforms. Currently, most product information are organized based on manually curated…

Visual autoregressive (VAR) models generate images through next-scale prediction, naturally achieving coarse-to-fine, fast, high-fidelity synthesis mirroring human perception. In practice, this hierarchy can drift at inference time, as…

Current transformers discard their rich latent residual stream between positions, reconstructing latent reasoning context at each new position and leaving potential reasoning capacity untapped. The State Stream Transformer (SST) V2 enables…

Standard classification models often map inputs directly to labels without explicit reasoning, potentially limiting their performance, robustness, and interpretability. This paper introduces a novel two-stage approach to enhance text…

While chains-of-thought (CoT) have advanced complex reasoning in multimodal large language models (MLLMs), existing methods remain confined to text or static visual domains, often faltering in dynamic spatial reasoning tasks. To bridge this…

Retrieval-augmented generation (RAG) has emerged as a promising technology for addressing hallucination issues in the responses generated by large language models (LLMs). Existing studies on RAG primarily focus on applying semantic-based…

Large language models (LLMs) solve complex problems by generating multi-step reasoning traces. Yet these traces are typically analyzed from only one of two perspectives: the sequence of tokens across different reasoning steps in the…

Test-time compute has emerged as a powerful paradigm for improving the performance of large language models (LLMs), where generating multiple outputs or refining individual chains can significantly boost answer accuracy. However, existing…

Generative models have recently demonstrated strong potential in multi-behavior recommendation systems, leveraging the expressive power of transformers and tokenization to generate personalized item sequences. However, their adoption is…

Despite rapid progress, embodied agents still struggle with long-horizon manipulation that requires maintaining spatial consistency, causal dependencies, and goal constraints. A key limitation of existing approaches is that task reasoning…

We present Thinking with Generated Images, a novel paradigm that fundamentally transforms how large multimodal models (LMMs) engage with visual reasoning by enabling them to natively think across text and vision modalities through…

Large Language Model (LLM)-based generative recommendation has achieved notable success, yet its practical deployment is costly particularly due to excessive inference latency caused by autoregressive decoding. For lossless LLM decoding…

Semantic IDs (SIDs) define the generation space of generative recommendation and directly determine its personalization ceiling. However, existing tokenizers are trained independently with retrieval objectives, leaving personalization…

Large language models (LLMs) have recently demonstrated remarkable success in mathematical reasoning. Despite progress in methods like chain-of-thought prompting and self-consistency sampling, these advances often focus on final correctness…

Generative models for Information Retrieval, where ranking of documents is viewed as the task of generating a query from a document's language model, were very successful in various IR tasks in the past. However, with the advent of modern…

We introduce Spatial Reasoning Models (SRMs), a framework to perform reasoning over sets of continuous variables via denoising generative models. SRMs infer continuous representations on a set of unobserved variables, given observations on…

Test-time compute is emerging as a new paradigm for enhancing language models' complex multi-step reasoning capabilities, as demonstrated by the success of OpenAI's o1 and o3, as well as DeepSeek's R1. Compared to explicit reasoning in…

Generative large language models as tools in the legal domain have the potential to improve the justice system. However, the reasoning behavior of current generative models is brittle and poorly understood, hence cannot be responsibly…