Related papers: Rebalancing Contrastive Alignment with Bottlenecke…

Multimodal Large Language Models have demonstrated remarkable capabilities in video understanding, yet face prohibitive computational costs and performance degradation from ''context rot'' due to massive visual token redundancy. Existing…

The success of contextual word representations and advances in neural information retrieval have made dense vector-based retrieval a standard approach for passage and document ranking. While effective and efficient, dual-encoders are…

We focus on contrastive methods for self-supervised video representation learning. A common paradigm in contrastive learning is to construct positive pairs by sampling different data views for the same instance, with different data…

Visual Reinforcement Learning (RL) agents must learn to act based on high-dimensional image data where only a small fraction of the pixels is task-relevant. This forces agents to waste exploration and computational resources on irrelevant…

CLIP (Contrastive Language-Image Pre-training) uses contrastive learning from noise image-text pairs to excel at recognizing a wide array of candidates, yet its focus on broad associations hinders the precision in distinguishing subtle…

Large Language Models (LLMs) demonstrate remarkable capabilities, yet struggle with hallucination and outdated knowledge when tasked with complex knowledge reasoning, resulting in factually incorrect outputs. Previous studies have attempted…

Representation learning on text-attributed graphs (TAGs) integrates structural connectivity with rich textual semantics, enabling applications in diverse domains. Current methods largely rely on contrastive learning to maximize cross-modal…

Prevailing methods for training Large Language Models (LLMs) as text encoders rely on contrastive losses that treat the model as a black box function, discarding its generative and reasoning capabilities in favor of static embeddings. We…

Text-to-video retrieval systems have recently made significant progress by utilizing pre-trained models trained on large-scale image-text pairs. However, most of the latest methods primarily focus on the video modality while disregarding…

Conventional Generative Adversarial Networks (GANs) for text generation tend to have issues of reward sparsity and mode collapse that affect the quality and diversity of generated samples. To address the issues, we propose a novel…

Retrieval-Augmented Generation (RAG) faces a core bottleneck with knowledge-sparse and semantically ambiguous long-tail queries, where retrieval noise distorts reasoning and necessitates costly post-processing. To tackle this, we propose…

Visual-Semantic Embedding (VSE) is a prevalent approach in image-text retrieval by learning a joint embedding space between the image and language modalities where semantic similarities would be preserved. The triplet loss with…

Reinforcement learning has recently been explored to improve text-to-image generation, yet applying existing GRPO algorithms to autoregressive (AR) image models remains challenging. The instability of the training process easily disrupts…

The dominant paradigm for Audio-Text Retrieval (ATR) relies on dual-encoder architectures optimized via mini-batch contrastive learning. However, restricting optimization to local in-batch samples creates a fundamental limitation we term…

Zero-shot video moment retrieval (ZVMR) is the task of localizing a temporal moment within an untrimmed video using a natural language query without relying on task-specific training data. The primary challenge in this setting lies in the…

Recent advances in audio-visual learning have shown promising results in learning representations across modalities. However, most approaches rely on global audio representations that fail to capture fine-grained temporal correspondences…

Legal document retrieval and judgment prediction are crucial tasks in intelligent legal systems. In practice, determining whether two documents share the same judgments is essential for establishing their relevance in legal retrieval.…

Retrieval-augmented generation integrates the capabilities of large language models with relevant information retrieved from an extensive corpus, yet encounters challenges when confronted with real-world noisy data. One recent solution is…

Recent progress in video-text retrieval has been driven largely by advancements in model architectures and training strategies. However, the representation learning capabilities of videotext retrieval models remain constrained by lowquality…

While mel-spectrograms have been widely utilized as intermediate representations in zero-shot text-to-speech (TTS), their inherent redundancy leads to inefficiency in learning text-speech alignment. Compact VAE-based latent representations…