…Existing explanations often focus on surface signals, such as lexical matches, token alignments, or post-hoc textual rationales, and thus provide limited insight into the latent factors that shape dense retrieval behavior…
…We first identify two fundamental limitations of naïve learnable memory architectures in long-horizon extrapolation , namely computational inefficiency and attention dispersion . Through a systematic analysis of attention dispersion , we propose DecMem, a…
…AI-generated summary Reinforcement learning has emerged as a powerful tool for improving diffusion-based text-to-image models, but existing methods are largely limited to single-task optimization. Extending RL to…
…Existing methods are largely limited to exact matching within a single modality, failing to capture cross-modal semantic relationships. To bridge this gap, we present AnalogRetriever, a unified tri-modal retrieval framework…
…Bohan Hou , , , , , , , Abstract InterLV-Search benchmark evaluates interleaved language-vision agentic search by repeatedly using textual and visual evidence to condition later search, revealing current systems' limitations in visual evidence seeking and…
…Two bottlenecks limit current systems. First, existing tool-use harness es treat images returned by search, browsing, or transformation as transient outputs, so intermediate visual evidence cannot be re-consumed by later…
…Agents have shown strong capability in multi-step information retrieval, reasoning, and long-form report generation, but existing benchmarks and systems remain predominantly text-centric, with limited evaluation of whether visual elements…
…Furthermore, we propose a hybrid approach that combines the strong geometry and material transformations of diffusion-based methods with the distribution-matching capabilities of image-to-image translation techniques. Through experiments, it…
…AI-generated summary Reinforcement learning with verifiable rewards, particularly Group Relative Policy Optimization (GRPO), has significantly advanced the reasoning capabilities of Large Language Models (LLMs). However, in complex tasks, GRPO frequently suffers…
…This capability is increasingly important for agentic search systems , where retrievers must provide complementary evidence across iterative search and synthesis. However, existing work remains limited on both evaluation and training: benchmarks such…