Related papers: Cross-attention for State-based model RWKV-7

Recent vision-language models have achieved tremendous advances. However, their computational costs are also escalating dramatically, making model acceleration exceedingly critical. To pursue more efficient vision-language Transformers,…

Large Language Models (LLMs) have been widely adopted to process long-context tasks. However, the large memory overhead of the key-value (KV) cache poses significant challenges in long-context scenarios. Existing training-free KV cache…

Vision-Language Models (vLLMs) have emerged as powerful architectures for joint reasoning over visual and textual inputs, enabling breakthroughs in image captioning, cross modal retrieval, and multimodal dialogue. However, as these models…

The efficacy of Large Language Models (LLMs) in long-context tasks is often hampered by the substantial memory footprint and computational demands of the Key-Value (KV) cache. Current compression strategies, including token eviction and…

Traditional multimodal learning approaches require expensive alignment pre-training to bridge vision and language modalities, typically projecting visual features into discrete text token spaces. We challenge both fundamental assumptions…

Efficient key-value (KV) cache compression is critical for scaling transformer-based Large Language Models (LLMs) in long sequences and resource-limited settings. Existing methods evict tokens based on their positions or importance scores,…

Achieving ID-preserving text-to-video (T2V) generation remains challenging despite recent advances in diffusion-based models. Existing approaches often fail to capture fine-grained facial dynamics or maintain temporal identity coherence. To…

Long-context Large Language Models (LLMs) enable powerful applications but incur high memory costs due to the key-value states (KV-Cache). Recent studies attempt to share KV-Cache across layers, but these approaches either require expensive…

Image restoration faces challenges including ineffective feature fusion, computational bottlenecks and inefficient diffusion processes. To address these, we propose DiffRWKVIR, a novel framework unifying Test-Time Training (TTT) with…

We introduce Skywork R1V, a multimodal reasoning model extending the an R1-series Large language models (LLM) to visual modalities via an efficient multimodal transfer method. Leveraging a lightweight visual projector, Skywork R1V…

Wide-angle videos in few-shot action recognition (FSAR) effectively express actions within specific scenarios. However, without a global understanding of both subjects and background, recognizing actions in such samples remains challenging…

Remote Sensing Image-Text Retrieval (RSITR) plays a critical role in geographic information interpretation, disaster monitoring, and urban planning by establishing semantic associations between image and textual descriptions. Existing…

Transfer learning is an emerging paradigm for leveraging multiple sources to improve the statistical inference on a single target. In this paper, we propose a novel approach named residual importance weighted transfer learning (RIW-TL) for…

Windowed attention mechanisms were introduced to mitigate the issue of excessive computation inherent in global attention mechanisms. In this paper, we present FwNet-ECA, a novel method that utilizes Fourier transforms paired with learnable…

Associating driver attention with driving scene across two fields of views (FOVs) is a hard cross-domain perception problem, which requires comprehensive consideration of cross-view mapping, dynamic driving scene analysis, and driver status…

Recursion is a prominent feature of human language, and fundamentally challenging for self-attention due to the lack of an explicit recursive-state tracking mechanism. Consequently, Transformer language models poorly capture long-tail…

We study Latent Recurrent Transformer (LRT), a lightweight augmentation of autoregressive transformers that reuses a high-level source-layer hidden state from the previous token as recurrent memory for the next token. Because this source…

Semantic Scene Completion (SSC) aims to generate a complete semantic scene from an incomplete input. Existing approaches often employ dense network architectures with a high parameter count, leading to increased model complexity and…

This paper considers contrastive training for cross-modal 0-shot transfer wherein a pre-trained model in one modality is used for representation learning in another domain using pairwise data. The learnt models in the latter domain can then…

We present a lightweight model for high resolution portrait matting. The model does not use any auxiliary inputs such as trimaps or background captures and achieves real time performance for HD videos and near real time for 4K. Our model is…