Cluster-Wise Spatio-Temporal Masking for Efficient Video-Language Pretraining

Large-scale video-language pretraining enables strong generalization across multimodal tasks but often incurs prohibitive computational costs. Although recent advances in masked visual modeling help mitigate this issue, they still suffer from two fundamental limitations: severe visual information loss under high masking ratios and temporal information leakage caused by inter-frame correlations. To address these challenges, we propose ClusterSTM, a Cluster-Wise Spatio-Temporal Masking strategy for efficient video-language pretraining. ClusterSTM first performs intra-frame clustering to partition visual tokens into multiple semantically independent clusters, then conducts cluster-wise masking by retaining the token with the highest temporal density within each cluster. Our masking strategy ensure that the retained tokens capture holistic video content while exhibit strong temporal correlation. Additionally, we introduce a video-text relevance reconstruction objective that aligns high-level multimodal semantics beyond conventional visual reconstruction. Extensive experiments across multiple benchmarks demonstrate that ClusterSTM achieves superior performance on video-text retrieval, video question answering, and video captioning tasks, establishing a new state-of-the-art among efficient video-language models.

From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents

While multimodal large language models have demonstrated impressive short-term reasoning, they struggle with long-horizon video understanding due to limited context windows and static memory mechanisms that fail to mirror human cognitive efficiency. Existing paradigms typically fall into two extremes: vision-centric methods that incur high latency and redundancy through dense visual accumulation, or text-centric approaches that suffer from detail loss and hallucination via aggressive captioning. To bridge this gap, we propose MM-Mem, a pyramidal multimodal memory architecture grounded in Fuzzy-Trace Theory. MM-Mem structures memory hierarchically into a Sensory Buffer, Episodic Stream, and Symbolic Schema, enabling the progressive distillation of fine-grained perceptual traces (verbatim) into high-level semantic schemas (gist). Furthermore, to govern the dynamic construction of memory, we derive a Semantic Information Bottleneck objective and introduce SIB-GRPO to optimize the trade-off between memory compression and task-relevant information retention. In inference, we design an entropy-driven top-down memory retrieval strategy, which first tries with the abstract Symbolic Schema and progressively "drills down" to the Sensory Buffer and Episodic Stream under high uncertainty. Extensive experiments across 4 benchmarks confirm the effectiveness of MM-Mem on both offline and streaming tasks, demonstrating robust generalization and validating the effectiveness of cognition-inspired memory organization. Code is available at https://github.com/EliSpectre/MM-Mem.

EPRBench: A High-Quality Benchmark Dataset for Event Stream Based Visual Place Recognition

Event stream-based Visual Place Recognition (VPR) is an emerging research direction that offers a compelling solution to the instability of conventional visible-light cameras under challenging conditions such as low illumination, overexposure, and high-speed motion. Recognizing the current scarcity of dedicated datasets in this domain, we introduce EPRBench, a high-quality benchmark specifically designed for event stream-based VPR. EPRBench comprises 10K event sequences and 65K event frames, collected using both handheld and vehicle-mounted setups to comprehensively capture real-world challenges across diverse viewpoints, weather conditions, and lighting scenarios. To support semantic-aware and language-integrated VPR research, we provide LLM-generated scene descriptions, subsequently refined through human annotation, establishing a solid foundation for integrating LLMs into event-based perception pipelines. To facilitate systematic evaluation, we implement and benchmark 15 state-of-the-art VPR algorithms on EPRBench, offering a strong baseline for future algorithmic comparisons. Furthermore, we propose a novel multi-modal fusion paradigm for VPR: leveraging LLMs to generate textual scene descriptions from raw event streams, which then guide spatially attentive token selection, cross-modal feature fusion, and multi-scale representation learning. This framework not only achieves highly accurate place recognition but also produces interpretable reasoning processes alongside its predictions, significantly enhancing model transparency and explainability. The dataset and source code will be released on https://github.com/Event-AHU/Neuromorphic_ReID

DeltaKV: Residual-Based KV Cache Compression via Long-Range Similarity

The deployment of efficient long-context LLMs in applications like autonomous agents, long-chain reasoning, and creative writing is fundamentally bottlenecked by the linear growth of KV cache memory. Existing compression and eviction methods often struggle to balance accuracy, compression ratio, and hardware efficiency. We propose DeltaKV, a residual-based KV cache compression framework motivated by two empirical findings: long-range inter-token similarity and highly shared latent components in KV representations. Instead of discarding tokens, DeltaKV encodes semantic residuals relative to retrieved historical references, preserving fidelity while substantially reducing storage. To translate compression gains into real system speedups, we further introduce Sparse-vLLM, a high-performance inference engine with decoupled memory management and kernels optimized for sparse and irregular KV layouts. Experiments show that DeltaKV reduces KV cache memory to 29\% of the original while maintaining near-lossless accuracy on LongBench, SCBench, and AIME. When integrated with Sparse-vLLM, it achieves up to 2$\times$ throughput improvement over vLLM in long-context scenarios, demonstrating a practical path toward scalable long-context LLM deployment. Code, model checkpoints, and datasets are available at https://github.com/CURRENTF/Sparse-vLLM.

MirrorLA: Reflecting Feature Map for Vision Linear Attention

Linear attention significantly reduces the computational complexity of Transformers from quadratic to linear, yet it consistently lags behind softmax-based attention in performance. We identify the root cause of this degradation as the non-negativity constraint imposed on kernel feature maps: standard projections like ReLU act as "passive truncation" operators, indiscriminately discarding semantic information residing in the negative domain. We propose MirrorLA, a geometric framework that substitutes passive truncation with active reorientation. By leveraging learnable Householder reflections, MirrorLA rotates the feature geometry into the non-negative orthant to maximize information retention. Our approach restores representational density through a cohesive, multi-scale design: it first optimizes local discriminability via block-wise isometries, stabilizes long-context dynamics using variance-aware modulation to diversify activations, and finally, integrates dispersed subspaces via cross-head reflections to induce global covariance mixing. MirrorLA achieves state-of-the-art performance across standard benchmarks, demonstrating that strictly linear efficiency can be achieved without compromising representational fidelity.

Seeing Through the Chain: Mitigate Hallucination in Multimodal Reasoning Models via CoT Compression and Contrastive Preference Optimization

While multimodal reasoning models (MLRMs) have exhibited impressive capabilities, they remain prone to hallucinations, and effective solutions are still underexplored. In this paper, we experimentally analyze the hallucination cause and propose C3PO, a training-based mitigation framework comprising \textbf{C}hain-of-Thought \textbf{C}ompression and \textbf{C}ontrastive \textbf{P}reference \textbf{O}ptimization. Firstly, we identify that introducing reasoning mechanisms exacerbates models' reliance on language priors while overlooking visual inputs, which can produce CoTs with reduced visual cues but redundant text tokens. To this end, we propose to selectively filter redundant thinking tokens for a more compact and signal-efficient CoT representation that preserves task-relevant information while suppressing noise. In addition, we observe that the quality of the reasoning trace largely determines whether hallucination emerges in subsequent responses. To leverage this insight, we introduce a reasoning-enhanced preference tuning scheme that constructs training pairs using high-quality AI feedback. We further design a multimodal hallucination-inducing mechanism that elicits models' inherent hallucination patterns via carefully crafted inducers, yielding informative negative signals for contrastive correction. We provide theoretical justification for the effectiveness and demonstrate consistent hallucination reduction across diverse MLRMs and benchmarks.

CLIP-Guided Adaptable Self-Supervised Learning for Human-Centric Visual Tasks

Human-centric visual analysis plays a pivotal role in diverse applications, including surveillance, healthcare, and human-computer interaction. With the emergence of large-scale unlabeled human image datasets, there is an increasing need for a general unsupervised pre-training model capable of supporting diverse human-centric downstream tasks. To achieve this goal, we propose CLASP (CLIP-guided Adaptable Self-suPervised learning), a novel framework designed for unsupervised pre-training in human-centric visual tasks. CLASP leverages the powerful vision-language model CLIP to generate both low-level (e.g., body parts) and high-level (e.g., attributes) semantic pseudo-labels. These multi-level semantic cues are then integrated into the learned visual representations, enriching their expressiveness and generalizability. Recognizing that different downstream tasks demand varying levels of semantic granularity, CLASP incorporates a Prompt-Controlled Mixture-of-Experts (MoE) module. MoE dynamically adapts feature extraction based on task-specific prompts, mitigating potential feature conflicts and enhancing transferability. Furthermore, CLASP employs a multi-task pre-training strategy, where part- and attribute-level pseudo-labels derived from CLIP guide the representation learning process. Extensive experiments across multiple benchmarks demonstrate that CLASP consistently outperforms existing unsupervised pre-training methods, advancing the field of human-centric visual analysis.

Splatwizard: A Benchmark Toolkit for 3D Gaussian Splatting Compression

The recent advent of 3D Gaussian Splatting (3DGS) has marked a significant breakthrough in real-time novel view synthesis. However, the rapid proliferation of 3DGS-based algorithms has created a pressing need for standardized and comprehensive evaluation tools, especially for compression task. Existing benchmarks often lack the specific metrics necessary to holistically assess the unique characteristics of different methods, such as rendering speed, rate distortion trade-offs memory efficiency, and geometric accuracy. To address this gap, we introduce Splatwizard, a unified benchmark toolkit designed specifically for benchmarking 3DGS compression models. Splatwizard provides an easy-to-use framework to implement new 3DGS compression model and utilize state-of-the-art techniques proposed by previous work. Besides, an integrated pipeline that automates the calculation of key performance indicators, including image-based quality metrics, chamfer distance of reconstruct mesh, rendering frame rates, and computational resource consumption is included in the framework as well. Code is available at https://github.com/splatwizard/splatwizard

A Semantically Enhanced Generative Foundation Model Improves Pathological Image Synthesis

The development of clinical-grade artificial intelligence in pathology is limited by the scarcity of diverse, high-quality annotated datasets. Generative models offer a potential solution but suffer from semantic instability and morphological hallucinations that compromise diagnostic reliability. To address this challenge, we introduce a Correlation-Regulated Alignment Framework for Tissue Synthesis (CRAFTS), the first generative foundation model for pathology-specific text-to-image synthesis. By leveraging a dual-stage training strategy on approximately 2.8 million image-caption pairs, CRAFTS incorporates a novel alignment mechanism that suppresses semantic drift to ensure biological accuracy. This model generates diverse pathological images spanning 30 cancer types, with quality rigorously validated by objective metrics and pathologist evaluations. Furthermore, CRAFTS-augmented datasets enhance the performance across various clinical tasks, including classification, cross-modal retrieval, self-supervised learning, and visual question answering. In addition, coupling CRAFTS with ControlNet enables precise control over tissue architecture from inputs such as nuclear segmentation masks and fluorescence images. By overcoming the critical barriers of data scarcity and privacy concerns, CRAFTS provides a limitless source of diverse, annotated histology data, effectively unlocking the creation of robust diagnostic tools for rare and complex cancer phenotypes.

Training-free Context-adaptive Attention for Efficient Long Context Modeling

Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of natural language processing tasks. These capabilities stem primarily from the self-attention mechanism, which enables modeling of long-range dependencies. However, the quadratic complexity of self-attention with respect to sequence length poses significant computational and memory challenges, especially as sequence length extends to extremes. While various sparse attention and KV cache compression methods have been proposed to improve efficiency, they often suffer from limitations such as reliance on fixed patterns, inability to handle both prefilling and decoding stages, or the requirement for additional training. In this paper, we propose Training-free Context-adaptive Attention (TCA-Attention), a training-free sparse attention mechanism that selectively attends to only the informative tokens for efficient long-context inference. Our method consists of two lightweight phases: i) an offline calibration phase that determines head-specific sparsity budgets via a single forward pass, and ii) an online token selection phase that adaptively retains core context tokens using a lightweight redundancy metric. TCA-Attention provides a unified solution that accelerates both prefilling and decoding while reducing KV cache memory footprint, without requiring parameter updates or architectural changes. Theoretical analysis shows that our approach maintains bounded approximation error. Extensive experiments demonstrate that TCA-Attention achieves a 2.8$\times$ speedup and reduces KV cache by 61% at 128K context length while maintaining performance comparable to full attention across various benchmarks, offering a practical plug-and-play solution for efficient long-context inference.