3462 papers
The paper introduces InternVL-U, a lightweight 4B-parameter unified multimodal model that democratizes advanced understanding, reasoning, generation, and editing capabilities by employing a modular architecture and a reasoning-centric data synthesis pipeline, achieving superior performance-efficiency balance that outperforms significantly larger baselines like BAGEL.
The paper introduces DISPLAY, a framework for generating controllable and physically consistent human-object interaction videos by utilizing sparse motion guidance (wrist coordinates and object bounding boxes), an object-stressed attention mechanism, and a multi-task auxiliary training strategy to overcome limitations in flexibility, generalization, and data scarcity.
This paper presents a comparative study of five cooperative localization algorithms in featureless, GPS-denied environments, revealing that while Sequential and Standard methods offer high accuracy at the cost of filter inconsistency, Covariance Intersection provides the most balanced trade-off between accuracy and robustness for safety-critical applications.
The TREC 2025 RAG Track advances research on trustworthy retrieval-augmented generation systems by introducing complex narrative queries, leveraging the MS MARCO V2.1 corpus, and employing a multi-faceted evaluation framework to foster innovation in context-aware, factually grounded responses.
This paper introduces CourtSI, a large-scale dataset and benchmark for evaluating spatial intelligence in vision-language models within sports scenarios, revealing significant performance gaps in existing models while demonstrating that fine-tuning on this data substantially improves accuracy and generalization.
This paper demonstrates through game-theoretic analysis and simulation that the non-cooperative behavior of nodes under the 802.11 DCF and 802.11e MAC protocols leads to inefficient Nash equilibria, whereas decoupling channel allocation from individual transmission strategies can achieve superior throughput for all competing nodes.
This paper addresses the problem of role classification in enterprise networks by introducing two practical algorithms that group hosts based on evolving connection patterns to simplify network management and enhance monitoring accuracy, demonstrating their effectiveness through commercial implementation and significant reduction in host grouping complexity.
WikiCLIP is an efficient contrastive framework for open-domain visual entity recognition that leverages large language model embeddings enhanced by a Vision-Guided Knowledge Adaptor and Hard Negative Synthesis to significantly outperform generative baselines while reducing inference latency by nearly 100 times.
This paper identifies a structural gradient failure in Chamfer distance optimization that causes point cloud collapse, demonstrating that introducing non-local coupling mechanisms is a necessary condition to suppress this collapse and achieve successful 3D shape optimization.
This paper demonstrates that redesigning database systems to adopt out-of-place writes, exemplified by a modified LeanStore, significantly reduces write amplification and boosts throughput across diverse OLTP benchmarks while enabling support for modern SSD interfaces like ZNS and FDP.
This paper proposes an interpretable text-motion retrieval framework that represents 3D human motion as joint-angle pseudo-images processed by Vision Transformers and aligns them with text via a token-wise late interaction mechanism, thereby overcoming the limitations of global-embedding methods by capturing fine-grained correspondences and improving retrieval accuracy.
This paper proposes a novel unsupervised domain adaptation framework based on a reformulated Margin Disparity Discrepancy to bridge the modality gap between annotated CT and unannotated interventional CBCT scans, achieving state-of-the-art performance in liver segmentation for both unsupervised and few-shot settings.
This paper proposes a principled token pruning framework for late-interaction retrieval models that leverages Voronoi cell estimation in hyperspace geometry to reduce index storage overhead while maintaining retrieval performance and enhancing interpretability.
This paper introduces the concept of Whole Slide Difficulty (WSD), derived from diagnostic disagreements between expert and non-expert pathologists, and demonstrates that leveraging this metric through multi-task learning or weighted loss functions significantly improves the accuracy of prostate cancer Gleason grading in Multiple Instance Learning models, particularly for higher-grade cases.
This paper introduces KDMR, a novel framework that formulates humanoid motion retargeting as a multi-contact whole-body trajectory optimization problem incorporating rigid-body dynamics and ground reaction forces to generate physically consistent, dynamically feasible locomotion trajectories that significantly outperform purely kinematic methods in both motion quality and downstream control policy performance.
This paper establishes that Tetris clearing and survival are NP-hard for any single tetromino type except the O-piece under the Super Rotation System, disproving a long-standing conjecture about the I-piece, while simultaneously providing polynomial-time algorithms for cases involving only dominoes or $1\times k$ pieces under specific initial board conditions.
ReCoSplat is an autoregressive feed-forward Gaussian Splatting model that overcomes the training-inference pose mismatch dilemma through a novel Render-and-Compare module and achieves state-of-the-art online novel view synthesis with efficient long-sequence handling via hybrid KV cache compression.
TiPToP is a modular, open-vocabulary robotic planning system that integrates pretrained vision foundation models with a Task and Motion Planner to solve multi-step manipulation tasks from RGB images and natural language instructions without requiring any robot-specific training data, achieving performance comparable to or better than fine-tuned vision-language-action models while enabling detailed failure mode analysis.
This paper introduces a general framework that extends Knowledge Compilation to Satisfiability Modulo Theories (SMT) by combining input formulas with pre-computed theory lemmas to enable polytime propositional-style querying of compiled SMT d-DNNFs.
This paper proposes a fully autonomous, state-of-the-art Integrated Air Defense system utilizing two BDI-based agents that employ meta-level plan reasoning to automatically detect threats, assess risks, and allocate weapons without manual intervention, thereby advancing network-centric warfare capabilities.