Related papers: Measuring Temporal Linguistic Emergence in Diffusi…

Spoken language diarization (LD) and related tasks are mostly explored using the phonotactic approach. Phonotactic approaches mostly use explicit way of language modeling, hence requiring intermediate phoneme modeling and transcribed data.…

Text-to-Image (T2I) models have advanced rapidly, yet they remain vulnerable to semantic leakage, the unintended transfer of semantically related features between distinct entities. Existing mitigation strategies are often…

Chain-of-Thought (CoT) reasoning improves multi-step mathematical problem solving in large language models but remains vulnerable to exposure bias and error accumulation, as early mistakes propagate irreversibly through autoregressive…

Distantly-labeled data can be used to scale up training of statistical models, but it is typically noisy and that noise can vary with the distant labeling technique. In this work, we propose a two-stage procedure for handling this type of…

Diffusion models have garnered significant attention since they can effectively learn complex multivariate Gaussian distributions, resulting in diverse, high-quality outcomes. They introduce Gaussian noise into training data and reconstruct…

Steering language model generation toward desired textual properties is essential for practical deployment, and inference-time methods are particularly appealing because they enable controllable generation without retraining. Recent work…

Standard decoding in Masked Diffusion Models (MDMs) is hindered by context rigidity: tokens are retained based on transient high confidence, often ignoring that early predictions lack full context. This creates cascade effects where initial…

Diffusion large language models (dLLMs) offer faster generation than autoregressive models while maintaining comparable quality, but existing watermarking methods fail on them due to their non-sequential decoding. Unlike autoregressive…

Pseudo-label learning methods have been widely applied in weakly-supervised temporal action localization. Existing works directly utilize weakly-supervised base model to generate instance-level pseudo-labels for training the…

Masked Diffusion Models (MDMs) as language models generate by iteratively unmasking tokens, yet their performance crucially depends on the inference time order of unmasking. Prevailing heuristics, such as confidence based sampling, are…

Masked diffusion models have demonstrated competitive results on various tasks including language generation. However, due to its iterative refinement process, the inference is often bottlenecked by slow and static sampling speed. To…

Diffusion large language models (dLLMs) gain speed by committing multiple tokens in parallel at each denoising step, but any erroneous commitment persists as conditioning context and biases every subsequent prediction. LLaDA2.1 repairs such…

This paper proposes a modeling framework for dynamic topic evolution based on temporal large language models. The method first uses a large language model to obtain contextual embeddings of text and then introduces a temporal decay function…

We study the emergence of multi-step reasoning in deep Transformer language models through a geometric and statistical-physics lens. Treating the hidden-state trajectory as a flow on an implicit Riemannian manifold, we analyze the layerwise…

Discrete diffusion models have recently emerged as strong alternatives to autoregressive language models, matching their performance through large-scale training. However, inference-time control remains relatively underexplored. In this…

Denoising diffusion probabilistic models for image inpainting aim to add the noise to the texture of image during the forward process and recover masked regions with unmasked ones of the texture via the reverse denoising process. Despite…

Diffusion language models (DLMs) offer a structural alternative to autoregressive generation: denoising can update tokens in arbitrary orders or in parallel rather than along a fixed left-to-right chain. In practice, fast DLM decoding…

We frame embedding inversion as conditional masked diffusion, recovering all tokens in parallel through iterative denoising rather than sequential autoregressive generation. A masked diffusion language model is conditioned on the target…

Reasoning models improve their problem-solving ability through inference-time scaling, allocating more compute via longer token budgets. Identifying which reasoning traces are likely to succeed remains a key opportunity: reliably predicting…

The local intrinsic dimension (LID) of data is a fundamental quantity in signal processing and learning theory, but quantifying the LID of high-dimensional, complex data has been a historically challenging task. Recent works have discovered…