Related papers: CORE: Context-Robust Remasking for Diffusion Langu…
Diffusion language models, as a promising alternative to traditional autoregressive (AR) models, enable faster generation and richer conditioning on bidirectional context. However, they suffer from a key discrepancy between training and…
The increasing use of token-based representations in language-driven applications has motivated wireless token communication, where tokens are treated as fundamental units for transmission. However, conventional communication systems…
Token representations influence the efficiency and adaptability of language models, yet conventional tokenization strategies impose rigid segmentation boundaries that do not adjust dynamically to evolving contextual relationships. The…
Recent advances in text-to-image personalization have enabled high-quality and controllable image synthesis for user-provided concepts. However, existing methods still struggle to balance identity preservation with text alignment. Our…
Low-dose computed tomography (CT) images suffer from noise and artifacts due to photon starvation and electronic noise. Recently, some works have attempted to use diffusion models to address the over-smoothness and training instability…
Traditionally, research in automated speech recognition has focused on local-first encoding of audio representations to predict the spoken phonemes in an utterance. Unfortunately, approaches relying on such hyper-local information tend to…
Passage retrieval aims to retrieve relevant passages from large collections of the open-domain corpus. Contextual Masked Auto-Encoding has been proven effective in representation bottleneck pre-training of a monolithic dual-encoder for…
Conditional diffusion models have exhibited superior performance in high-fidelity text-guided visual generation and editing. Nevertheless, prevailing text-guided visual diffusion models primarily focus on incorporating text-visual…
Generative diffusion models offer a natural choice for data augmentation when training complex vision models. However, ensuring reliability of their generative content as augmentation samples remains an open challenge. Despite a number of…
Masked diffusion models (MDM) are powerful generative models for discrete data that generate samples by progressively unmasking tokens in a sequence. Each token can take one of two states: masked or unmasked. We observe that token sequences…
Large Language Models (LLMs) often hallucinate, producing unfaithful or factually incorrect outputs by misrepresenting the provided context or incorrectly recalling internal knowledge. Recent studies have identified specific attention heads…
In-context generation significantly enhances Diffusion Transformers (DiTs) by enabling controllable image-to-image generation through reference examples. However, the resulting input concatenation drastically increases sequence length,…
Camouflaged Object Detection (COD) is a challenging task in computer vision due to the high similarity between camouflaged objects and their surroundings. Existing COD methods primarily employ semantic segmentation, which suffers from…
Recent endeavors in Multimodal Large Language Models (MLLMs) aim to unify visual comprehension and generation by combining LLM and diffusion models, the state-of-the-art in each task, respectively. Existing approaches rely on spatial visual…
A key challenge for iterative text generation is enabling models to efficiently identify and correct their own errors. We propose Review, Remask, Refine (R3), a relatively simple yet elegant framework that requires no additional model…
Diffusion large language models (dLLMs) generate text via iterative denoising but consistently underperform on multi-step reasoning. We hypothesize this gap stems from a coordination problem: AR models build coherence token-by-token, while…
In document-level neural machine translation (DocNMT), multi-encoder approaches are common in encoding context and source sentences. Recent studies \cite{li-etal-2020-multi-encoder} have shown that the context encoder generates noise and…
A challenge in mitigating social bias in fine-tuned language models (LMs) is the potential reduction in language modeling capability, which can harm downstream performance. Counterfactual data augmentation (CDA), a widely used method for…
The success of large-scale language models has established tokens as compact and meaningful units for natural-language representation, which motivates token communication over wireless channels, where tokens are considered fundamental units…
Text error correction aims to correct the errors in text sequences such as those typed by humans or generated by speech recognition models. Previous error correction methods usually take the source (incorrect) sentence as encoder input and…