稠密检索

Generative models have recently gained attention in recommendation systems by directly predicting item identifiers from user interaction sequences. However, existing methods suffer from significant information loss due to the separation of stages such as quantization and sequence modeling, hindering their ability to achieve the modeling precision and accuracy of sequential dense retrieval techniques. Integrating generative and dense retrieval methods remains a critical challenge. To address this, we introduce the Cascaded Organized Bi-Represented generAtive retrieval (COBRA) framework, which innovatively integrates sparse semantic IDs and dense vectors through a cascading process. Our method alternates between generating these representations by first generating sparse IDs, which serve as conditions to aid in the generation of dense vectors. End-to-end training enables dynamic refinement of dense representations, capturing both semantic insights and collaborative signals from user-item interactions. During inference, COBRA employs a coarse-to-fine strategy, starting with sparse ID generation and refining them into dense vectors via the generative model. We further propose BeamFusion, an innovative approach combining beam search with nearest neighbor scores to enhance inference flexibility and recommendation diversity. Extensive experiments on public datasets and offline tests validate our method's robustness. Online A/B tests on a real-world advertising platform with over 200 million daily users demonstrate substantial improvements in key metrics, highlighting COBRA's practical advantages.

The demand for multimodal data processing drives the development of information technology. Cross-modal hash retrieval has attracted much attention because it can overcome modal differences and achieve efficient retrieval, and has shown great application potential in many practical scenarios. Existing cross-modal hashing methods have difficulties in fully capturing the semantic information of different modal data, which leads to a significant semantic gap between modalities. Moreover, these methods often ignore the importance differences of channels, and due to the limitation of a single goal, the matching effect between hash codes is also affected to a certain extent, thus facing many challenges. To address these issues, we propose a Dynamic Masking and Auxiliary Hash Learning (AHLR) method for enhanced cross-modal retrieval. By jointly leveraging the dynamic masking and auxiliary hash learning mechanisms, our approach effectively resolves the problems of channel information imbalance and insufficient key information capture, thereby significantly improving the retrieval accuracy. Specifically, we introduce a dynamic masking mechanism that automatically screens and weights the key information in images and texts during the training process, enhancing the accuracy of feature matching. We further construct an auxiliary hash layer to adaptively balance the weights of features across each channel, compensating for the deficiencies of traditional methods in key information capture and channel processing. In addition, we design a contrastive loss function to optimize the generation of hash codes and enhance their discriminative power, further improving the performance of cross-modal retrieval. Comprehensive experimental results on NUS-WIDE, MIRFlickr-25K and MS-COCO benchmark datasets show that the proposed AHLR algorithm outperforms several existing algorithms.

As retrieval-augmented generation (RAG) becomes increasingly widespread, the role of information retrieval (IR) is shifting from retrieving information for human users to retrieving contextual knowledge for artificial intelligence (AI) systems, where relevance becomes difficult to define or annotate beforehand. To address this challenge, we propose R3, a Retrieval framework optimized for RAG through trial-and-feedback Reinforced contrastive learning. Unlike prior approaches that rely on annotated or synthetic data for supervised fine-tuning, R3 enables the retriever to dynamically explore and optimize relevance within the RAG environment. During training, the retrieved results interact with the environment to produce contrastive signals that automatically guide the retriever’s self-improvement. Extensive experiments across diverse tasks demonstrate that R3 improves RAG performance by 5.2% over the original retriever and surpasses state-of-the-art retrievers by 4.9%, while achieving comparable results to LLM-augmented retrieval and RAG systems built on post-trained or instruction-tuned LLMs. It is both efficient and practical, requiring only 4 GPUs and completing training within a single day.

While existing research on Multilingual CLIP (MCLIP) has prioritized model architecture design, our work uncovers a critical challenge in practical adaptation: fine-tuning MCLIP through a single source language risks diminishing its multilingual capabilities in downstream tasks due to cross-linguistic disparities. To bridge this gap, we systematically investigate the role of ‌token similarity‌ in cross-lingual transferability for image-text retrieval, establishing it as a key factor governing fine-tuning efficacy. Building on this insight, we propose two novel strategies to enhance efficiency while preserving multilinguality: 1) ‌TaPCL dynamically optimizes training by prioritizing linguistically distant language pairs during corpus sampling, reducing redundant computation, and 2) CiPCL enriches the source corpus with multilingual key terms, enabling targeted knowledge transfer without reliance on exhaustive parallel data. By strategically balancing token similarity and domain-critical information, our methods significantly lower computational costs and mitigate over-dependence on parallel corpora. Experimental evaluations across diverse datasets validate the effectiveness and scalability of our framework, demonstrating robust multilingual retention across languages. This work provides a principled pathway for adapting MCLIP to real-world scenarios, where computational efficiency and cross-lingual robustness are paramount. Our codes are available at https://github.com/tiggers23/TaPCL-CiPCL.

Efficient neural networks are essential for scaling machine learning models to real-time applications and resource-constrained environments. Fully-connected feedforward layers (FFLs) introduce computation and parameter count bottlenecks within neural network architectures. To address this challenge, in this work, we propose a new class of dense layers that generalize standard fully-connected feedforward layers, $\textbf{E}$fficient, $\textbf{U}$nified and $\textbf{Gen}$eral dense layers (EUGens). EUGens leverage random features to approximate standard FFLs and go beyond them by incorporating a direct dependence on the input norms in their computations. The proposed layers unify existing efficient FFL extensions and improve efficiency by reducing inference complexity from quadratic to linear time. They also lead to $\textbf{the first}$ unbiased algorithms approximating FFLs with arbitrary polynomial activation functions. Furthermore, EuGens reduce the parameter count and computational overhead while preserving the expressive power and adaptability of FFLs. We also present a layer-wise knowledge transfer technique that bypasses backpropagation, enabling efficient adaptation of EUGens to pre-trained models. Empirically, we observe that integrating EUGens into Transformers and MLPs yields substantial improvements in inference speed (up to $\textbf{27}$\%) and memory efficiency (up to $\textbf{30}$\%) across a range of tasks, including image classification, language model pre-training, and 3D scene reconstruction. Overall, our results highlight the potential of EUGens for the scalable deployment of large-scale neural networks in real-world scenarios.

We introduce the Region Encoder Network (REN), a fast and effective model for generating region-based image representations using point prompts. Recent methods combine class-agnostic segmenters (e.g., SAM) with patch-based image encoders (e.g., DINO) to produce compact and effective region representations, but they suffer from high computational cost due to the segmentation step. REN bypasses this bottleneck using a lightweight module that directly generates region tokens, enabling 60x faster token generation with 35x less memory, while also improving token quality. It uses a few cross-attention blocks that take point prompts as queries and features from a patch-based image encoder as keys and values to produce region tokens that correspond to the prompted objects. We train REN with three popular encoders—DINO, DINOv2, and OpenCLIP—and show that it can be extended to other encoders without dedicated training. We evaluate REN on semantic segmentation and retrieval tasks, where it consistently outperforms the original encoders in both performance and compactness, and matches or exceeds SAM-based region methods while being significantly faster. Notably, REN achieves state-of-the-art results on the challenging Ego4D VQ2D benchmark and outperforms proprietary LMMs on Visual Haystacks' single-needle challenge. The code and pretrained models are available at https://github.com/savya08/ren.

In this work, we observe a counterintuitive phenomenon in self-supervised learning (SSL): longer training may impair the performance of dense prediction tasks (e.g., semantic segmentation). We refer to this phenomenon as Self-supervised Dense Degradation (SDD) and demonstrate its consistent presence across sixteen state-of-the-art SSL methods with various losses, architectures, and datasets. When the model performs suboptimally on dense tasks at the end of training, measuring the performance during training becomes essential. However, evaluating dense performance effectively without annotations remains an open challenge. To tackle this issue, we introduce a Dense representation Structure Estimator (DSE), composed of a class-relevance measure and an effective dimensionality measure. The proposed DSE is both theoretically grounded and empirically validated to be closely correlated with the downstream performance. Based on this metric, we introduce a straightforward yet effective model selection strategy and a DSE-based regularization method. Experiments on sixteen SSL methods across four benchmarks confirm that model selection improves mIoU by $3.0\\%$ on average with negligible computational cost. Additionally, DSE regularization consistently mitigates the effects of dense degradation. Code is available at \url{https://github.com/EldercatSAM/SSL-Degradation}.

Sparse autoencoders (SAEs) are designed to extract interpretable features from language models by enforcing a sparsity constraint. Ideally, training an SAE would yield latents that are both sparse and semantically meaningful. However, many SAE latents activate frequently (i.e., are *dense*), raising concerns that they may be undesirable artifacts of the training procedure. In this work, we systematically investigate the geometry, function, and origin of dense latents and show that they are not only persistent but often reflect meaningful model representations. We first demonstrate that dense latents tend to form antipodal pairs that reconstruct specific directions in the residual stream, and that ablating their subspace suppresses the emergence of new dense features in retrained SAEs---suggesting that high density features are an intrinsic property of the residual space. We then introduce a taxonomy of dense latents, identifying classes tied to position tracking, context binding, entropy regulation, letter-specific output signals, part-of-speech, and principal component reconstruction. Finally, we analyze how these features evolve across layers, revealing a shift from structural features in early layers, to semantic features in mid layers, and final to output-oriented signals in the last layers of the model. Our findings indicate that dense latents serve functional roles in language model computation and should not be dismissed as training noise.

Video Temporal Grounding (VTG) aims to localize temporal segments in long, untrimmed videos that align with a given natural language query. This task typically comprises two subtasks: \textit{Moment Retrieval (MR)} and \textit{Highlight Detection (HD)}. While recent advances have been progressed by powerful pretrained vision-language models such as CLIP and InternVideo2, existing approaches commonly treat all text tokens uniformly during cross-modal attention, disregarding their distinct semantic roles. To validate the limitations of this approach, we conduct controlled experiments demonstrating that VTG models overly rely on [EOS]-driven global semantics while failing to effectively utilize word-level signals, which limits their ability to achieve fine-grained temporal alignment. Motivated by this limitation, we propose DualGround, a dual-branch architecture that explicitly separates global and local semantics by routing the [EOS] token through a sentence-level path and clustering word tokens into phrase-level units for localized grounding. Our method introduces (1) token-role-aware cross modal interaction strategies that align video features with sentence-level and phrase-level semantics in a structurally disentangled manner, and (2) a joint modeling framework that not only improves global sentence-level alignment but also enhances fine-grained temporal grounding by leveraging structured phrase-aware context. This design allows the model to capture both coarse and localized semantics, enabling more expressive and context-aware video grounding. DualGround achieves state-of-the-art performance on both Moment Retrieval and Highlight Detection tasks across QVHighlights and Charades-STA benchmarks, demonstrating the effectiveness of disentangled semantic modeling in video-language alignment.

Urban computing harnesses big data to decode complex urban dynamics and revolutionize location-based services. Traditional approaches have treated geospatial prediction tasks (e.g., estimating socio-economic indicators) and retrieval tasks (e.g., querying geographic objects) as isolated challenges, necessitating separate models with distinct training objectives. This fragmentation imposes significant computational burdens and limits cross-task synergy, despite advances in representation learning and multi-task foundation models. We present UrbanSparse, a pioneering framework that unifies geospatial prediction and retrieval through a novel sparse-dense representation architecture. By synergistically combining these tasks, UrbanSparse eliminates redundant systems while amplifying their mutual strengths. Our approach introduces two innovations: (1) Bloom filter-based sparse encodings that compress high-sparsity geographic queries and fine-grained text terms for retrieval effectiveness, and (2) a dense semantic codebook that captures granular urban features to boost prediction accuracy. A two-view contrastive learning mechanism further bridges urban objects, regions, and contexts. Experiments on real-world datasets demonstrate 25.16% gains in prediction accuracy and 20.76% improvements in retrieval precision over state-of-the-art baselines, alongside 65.97% faster training. These advantages position UrbanSparse as a scalable solution for large urban datasets. To our knowledge, this is the first unified framework bridging geospatial prediction and retrieval, opening new frontiers in data-driven urban intelligence.

Semantic Scene Completion (SSC) aims to reconstruct the 3D geometry and semantics of the surrounding environment. With dense voxel labels, prior works typically formulate SSC as a *dense segmentation task*, independently classifying each voxel. However, this paradigm neglects critical instance-centric discriminability, leading to instance-level incompleteness and adjacent ambiguities. To address this, we highlight a "free lunch" of SSC labels: the voxel-level class label has implicitly told the instance-level insight, which is ever-overlooked by the community. Motivated by this observation, we first introduce a training-free **Voxel-to-Instance (VoxNT) trick**: a simple yet effective method that freely converts voxel-level class labels into instance-level offset labels. Building on this, we further propose **VoxDet**, an instance-centric framework that reformulates the voxel-level SSC as *dense object detection* by decoupling it into two sub-tasks: offset regression and semantic prediction. Specifically, based on the lifted 3D volume, VoxDet first uses (a) Spatially-decoupled Voxel Encoder to generate disentangled feature volumes for the two sub-tasks, which learn task-specific spatial deformation in the densely projected tri-perceptive space. Then, we deploy (b) Task-decoupled Dense Predictor to address SSC via dense detection. Here, we first regress a 4D offset field to estimate distances (6 directions) between voxels and the corresponding object boundaries in the voxel space. The regressed offsets are then used to guide the instance-level aggregation in the classification branch, achieving instance-aware scene completion. VoxDet can be deployed on both camera and LiDAR input and jointly achieves state-of-the-art results on both benchmarks, which gives 63.0 IoU on the SemanticKITTI test set, **ranking 1$^{st}$** on the online leaderboard.

Dual encoder (DE) models, where a pair of matching query and document are embedded into similar vector representations, are widely used in information retrieval due to their simplicity and scalability. However, the Euclidean geometry of the embedding space limits the expressive power of DEs, which may compromise their quality. This paper investigates such limitations in the context of hierarchical retrieval (HR), where the document set has a hierarchical structure and the matching documents for a query are all of its ancestors. We first prove that DEs are feasible for HR as long as the embedding dimension is linear in the depth of the hierarchy and logarithmic in the number of documents. Then we study the problem of learning such embeddings in a standard retrieval setup where DEs are trained on samples of matching query and document pairs. Our experiments reveal a lost-in-the-long-distance phenomenon, where retrieval accuracy degrades for documents further away in the hierarchy. To address this, we introduce a pretrain-finetune recipe that significantly improves long-distance retrieval without sacrificing performance on closer documents. We experiment on a realistic hierarchy from WordNet for retrieving documents at various levels of abstraction, and show that pretrain-finetune boosts the recall on long-distance pairs from 19% to 76%. Finally, we demonstrate that our method improves retrieval of relevant products on a shopping queries dataset.

Multilayer perceptrons (MLPs) are an integral part of large language models, yet their dense representations render them difficult to understand, edit, and steer. Recent methods learn interpretable approximations via neuron-level sparsity, yet fail to faithfully reconstruct the original mapping--significantly increasing model's next-token cross-entropy loss. In this paper, we advocate for moving to layer-level sparsity to overcome the accuracy trade-off in sparse layer approximation. Under this paradigm, we introduce Mixture of Decoders (MxDs). MxDs generalize MLPs and Gated Linear Units, expanding pre-trained dense layers into tens of thousands of specialized sublayers. Through a flexible form of tensor factorization, each sparsely activating MxD sublayer implements a linear transformation with full-rank weights--preserving the original decoders' expressive capacity even under heavy sparsity. Experimentally, we show that MxDs significantly outperform state-of-the-art methods (e.g., Transcoders) on the sparsity-accuracy frontier in language models with up to 3B parameters. Further evaluations on sparse probing and feature steering demonstrate that MxDs learn similarly specialized features of natural language--opening up a promising new avenue for designing interpretable yet faithful decompositions. Our code is included at: https://github.com/james-oldfield/MxD.

Mixture of Experts (MoE) pretraining is more scalable than dense Transformer pretraining, because MoEs learn to route inputs to a sparse set of their feedforward parameters. However, this means that MoEs only receive a sparse backward update, leading to training instability and suboptimal performance. We present a lightweight approximation method that gives the MoE router a dense gradient update while continuing to sparsely activate its parameters. Our method, which we refer to as Default MoE, substitutes missing expert activations with default outputs consisting of an exponential moving average of expert outputs previously seen over the course of training. This allows the router to receive signals from every expert for each token, leading to significant improvements in training performance. Our Default MoE outperforms standard TopK routing in a variety of settings without requiring significant computational overhead.

Dense and versatile image representations underpin the success of virtually all computer vision applications. However, state-of-the-art networks, such as transformers, produce low-resolution feature grids, which are suboptimal for dense prediction tasks. To address this limitation, we present *FlowFeat*, a high-resolution and multi-task feature representation. The key ingredient behind FlowFeat is a novel distillation technique that embeds a distribution of plausible apparent motions, or *motion profiles*. By leveraging optical flow networks and diverse video data, we develop an effective self-supervised training framework that statistically approximates the apparent motion. With its remarkable level of spatial detail, FlowFeat encodes a compelling degree of geometric and semantic cues while exhibiting high temporal consistency. Empirically, FlowFeat significantly enhances the representational power of five state-of-the-art encoders and alternative upsampling strategies across three dense tasks: video object segmentation, monocular depth estimation and semantic segmentation. Training FlowFeat is computationally inexpensive and robust to inaccurate flow estimation, remaining highly effective even when using unsupervised flow networks. Our work takes a step forward towards reliable and versatile dense image representations.

Protein language models (PLMs) learn probability distributions over natural protein sequences. By learning from hundreds of millions of natural protein sequences, protein understanding and design capabilities emerge. Recent works have shown that scaling these models improves structure prediction, but does not seem to improve mutation understanding and representation quality for protein function prediction. We introduce PoET-2, a multimodal, retrieval-augmented protein foundation model that incorporates in-context learning of family-specific evolutionary constraints with optional structure conditioning to learn generative distributions over protein sequences. PoET-2 uses a hierarchical transformer encoder that is equivariant to sequence context ordering and a dual decoder architecture with both causal and masked language modeling objectives, allowing PoET-2 to operate in both fully generative and bidirectional representation learning modes. PoET-2 achieves state-of-the-art performance on zero-shot variant effect prediction, excelling at scoring variants with multiple mutations and challenging indel mutations. In supervised settings, PoET-2 embeddings outperform previous methods for learning sequence-function relationships, especially with small datasets. This work highlights the benefits of combining retrieval augmentation with multimodal, family-centric modeling for advancing protein foundation models.

We consider the problem of detecting a community of densely connected vertices in a high-dimensional bipartite graph of size $n_1 \times n_2$. Under the null hypothesis, the observed graph is drawn from a bipartite Erdos-Renyi distribution with connection probability $p_0$. Under the alternative hypothesis, there exists an unknown bipartite subgraph of size $k_1 \times k_2$ in which edges appear with probability $p_1 = p_0 + \delta$ for some $\delta > 0$, while all other edges outside the subgraph appear with probability $p_0$. Specifically, we provide non-asymptotic upper and lower bounds on the smallest signal strength $\delta^*$ that is both necessary and sufficient to ensure the existence of a test with small enough type one and type two errors. We also derive novel minimax-optimal tests achieving these fundamental limits when the underlying graph is sufficiently dense. Our proposed tests involve a combination of hard-thresholded nonlinear statistics of the adjacency matrix, the analysis of which may be of independent interest. In contrast with previous work, our non-asymptotic upper and lower bounds match for any configuration of $n_1,n_2, k_1,k_2$.

The 2023 Big ANN Challenge, held at NeurIPS 2023, focused on advancing the state-of-the-art in indexing data structures and search algorithms for practical variants of Approximate Nearest Neighbor (ANN) search that reflect its the growing complexity and diversity of workloads. Unlike prior challenges that emphasized scaling up classical ANN search (Simhadri et al., NeurIPS 2021), this competition addressed sparse, filtered, out-of-distribution, and streaming variants of ANNS. Participants developed and submitted innovative solutions that were evaluated on new standard datasets with constrained computational resources. The results showcased significant improvements in search accuracy and efficiency, with notable contributions from both academic and industrial teams. This paper summarizes the competition tracks, datasets, evaluation metrics, and the innovative approaches of the top-performing submissions, providing insights into the current advancements and future directions in the field of approximate nearest neighbor search.

Semantic retrieval is crucial for modern applications yet remains underexplored in current research. Existing datasets are limited to single languages, single images, or singular retrieval conditions, often failing to fully exploit the expressive capacity of visual information as evidenced by maintained performance when images are replaced with captions. However, practical retrieval scenarios frequently involve interleaved multi-condition queries with multiple images. Hence, this paper introduces MERIT, the first multilingual dataset for interleaved multi-condition semantic retrieval, comprising 320,000 queries with 135,000 products in 5 languages, covering 7 distinct product categories. Extensive experiments on MERIT identify existing models's critical limitation: focusing solely on global semantic information while neglecting specific conditional elements in queries. Consequently, we propose Coral, a novel fine-tuning framework that adapts pre-trained MLLMs by integrating embedding reconstruction to preserve fine-grained conditional elements and contrastive learning to extract comprehensive global semantics. Experiments demonstrate that Coral achieves a 45.9% performance improvement over conventional approaches on MERIT, with strong generalization capabilities validated across 8 established retrieval benchmarks. Collectively, our contributions—a novel dataset, identification of critical limitations in existing approaches, and an innovative fine-tuning framework—establish a foundation for future research in interleaved multi-condition semantic retrieval. **Data & Code**: [MERIT-2025.github.io](https://merit-2025.github.io)

Dense metric depth estimation has witnessed great developments in recent years. While single-image-based methods have demonstrated commendable performance in certain circumstances, they may encounter challenges regarding scale ambiguities and visual illusions in real world. Traditional depth-from-focus methods are constrained by low sampling rates during data acquisition. In this paper, we introduce a novel approach to enhance dense metric depth estimation by fusing events with image foundation models via a prompting approach. Specifically, we build Event-based Differential Focus Volumes (EDFV) using events triggered through focus sweeping, which are subsequently transformed into sparse metric depth maps. These maps are then utilized for prompting dense depth estimation via our proposed Event-based Depth Prompting Network. We further construct synthetic and real-captured datasets to facilitate the training and evaluation of both frame-based and event-based methods. Quantitative and qualitative results, including both in-domain and zero-shot experiments, demonstrate the superior performance of our method compared to existing approaches. Code and data will be available at https://github.com/liboyu02/EDFV/.