Knowledge catalogue
arXiv:2604.18313v1 Announce Type: new Abstract: Open-Vocabulary Temporal Action Detection (OV-TAD) aims to localize and classify action segments of unseen categories in untrimmed videos, where effecti
arXiv:2511.02830v2 Announce Type: replace Abstract: We propose DenseMarks - a new learned representation for human heads, enabling high-quality dense correspondences of human head images. For a 2D ima
arXiv:2604.17286v1 Announce Type: new Abstract: Visual Autoregressive (VAR) modeling inefficiently applies a fixed computational depth to each position when generating high-resolution images. While ex
arXiv:2604.18128v1 Announce Type: new Abstract: We study post-training W4A4 quantization in a controlled 300M-parameter SwiGLU decoder-only language model trained on 5B tokens of FineWeb-Edu, and ask
arXiv:2603.05743v3 Announce Type: replace Abstract: Although artificial intelligence (AI) and Human-Computer Interaction (HCI) systems are often presented as universal solutions, their design remains
arXiv:2604.16717v1 Announce Type: new Abstract: This paper addresses a critical safety gap in the use Automated Verbal Response Scoring (AVRS). We present a novel hybrid framework for troubled student
arXiv:2510.01801v2 Announce Type: replace Abstract: The rise of large language models (LLMs) has enabled the generation of highly persuasive spam reviews that closely mimic human writing. These review
arXiv:2604.16484v1 Announce Type: new Abstract: Deploying generative World-Action Models for manipulation is severely bottlenecked by redundant pixel-level reconstruction, O(T) memory scaling, and seq
arXiv:2512.12022v2 Announce Type: replace Abstract: Decentralized federated learning (DFL) has emerged as a promising paradigm that enables multiple clients to collaboratively train machine learning m
arXiv:2604.17585v1 Announce Type: new Abstract: Salient object detection (SOD) requires modeling both long-range contextual dependencies and fine-grained structural details, which remains challenging
arXiv:2604.16318v1 Announce Type: cross Abstract: Large language models (LLMs) and cross-encoder rerankers have gained attention for improving recommender systems, particularly in cold-start scenarios
arXiv:2601.03559v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) reasoning improves multi-step mathematical problem solving in large language models but remains vulnerable to exposure bias a
arXiv:2604.18510v1 Announce Type: cross Abstract: Open-weight language models can be rendered unsafe through several distinct interventions, but the resulting models may differ substantially in capabi
arXiv:2603.04881v2 Announce Type: replace Abstract: Differentially private learning is essential for training models on sensitive data, but empirical studies consistently show that it can degrade perf
arXiv:2604.17961v1 Announce Type: new Abstract: In this work, we introduce DifFoundMAD, a parameter-efficient D-MAD framework that exploits the generalisation capabilities of vision foundation models
arXiv:2604.18201v1 Announce Type: new Abstract: Diffusion models have emerged as powerful tools for a wide range of vision tasks, including text-guided image generation and editing. In this work, we e
arXiv:2604.16670v1 Announce Type: new Abstract: We present a framework leveraging a novel variant of the model-based diffusion algorithm to minimize the time required for a redundant dual-arm robot co
arXiv:2604.16431v1 Announce Type: new Abstract: Abrupt transitions between distinct dynamical regimes are a hallmark of complex systems. Grokking in deep neural networks provides a striking example --
arXiv:2602.05449v3 Announce Type: replace Abstract: While diffusion models have achieved great success in the field of video generation, this progress is accompanied by a rapidly escalating computatio
arXiv:2604.16391v1 Announce Type: cross Abstract: Vision-language-action (VLA) models have shown great potential in building generalist robots, but still face a dilemma-misalignment of 2D image foreca
arXiv:2604.18277v1 Announce Type: new Abstract: Accurate dynamical modeling is essential for simulation and control of embodied systems, yet first-principles models of electromechanical systems often
arXiv:2604.18143v1 Announce Type: cross Abstract: This paper investigates the off-policy evaluation (OPE) problem from a distributional perspective. Rather than focusing solely on the expectation of t
arXiv:2512.10906v2 Announce Type: replace-cross Abstract: We consider a class of finite-horizon, linear-quadratic stochastic control problems, where the probability distribution governing the noise pr
arXiv:2604.17568v1 Announce Type: new Abstract: Given only observational data X = g(Z), where both the latent variables Z and the generating process g are unknown, recovering Z is ill-posed without ad
arXiv:2604.18005v1 Announce Type: cross Abstract: Multi-agent systems (MAS) are increasingly used for open-ended idea generation, driven by the expectation that collective interaction will broaden the
arXiv:2604.08302v2 Announce Type: replace Abstract: We present DMax, a new paradigm for efficient diffusion language models (dLLMs). It mitigates error accumulation in parallel decoding, enabling aggr
arXiv:2604.17191v1 Announce Type: new Abstract: Multi-agent reinforcement learning (MARL) is crucial for AI systems that operate collaboratively in distributed and adversarial settings, particularly i
arXiv:2601.03066v2 Announce Type: replace Abstract: Large language models solve complex tasks by generating long reasoning chains, achieving higher accuracy at the cost of increased computational cost
arXiv:2604.17718v1 Announce Type: new Abstract: Many benchmarks show that large language models can answer direct questions about culture. We study a different question: do they also change how they s
arXiv:2604.18257v1 Announce Type: cross Abstract: Query auto-completion (QAC) has been widely studied in the context of web search, yet remains underexplored for in-document search, which we term DocQ
arXiv:2604.18508v1 Announce Type: cross Abstract: Many recent document embedding models are trained on document-as-image representations, embedding rendered pages as images rather than the underlying
arXiv:2603.11024v2 Announce Type: replace Abstract: VLMs have become increasingly proficient at a range of computer vision tasks, such as visual question answering and object detection. This includes
arXiv:2604.18161v1 Announce Type: new Abstract: In policy gradient reinforcement learning, access to a differentiable model enables 1st-order gradient estimation that accelerates learning compared to
arXiv:2604.17628v1 Announce Type: new Abstract: Wales' political landscape has been marked by growing accusations of bias in Welsh media. This paper takes the first computational step toward testing t
arXiv:2604.17943v1 Announce Type: new Abstract: Open-domain RAG benchmarks over public corpora can overestimate deployment performance due to pretraining overlap and weak attribution requirements. We
arXiv:2604.18256v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models provide a structured approach to combining specialized neural networks and offer greater interpretability than conventio
arXiv:2510.07248v3 Announce Type: replace Abstract: Small language models (SLMs) enable scalable tool-augmented multi-agent systems where multiple SLMs handle subtasks orchestrated by a powerful coord
arXiv:2604.17244v1 Announce Type: new Abstract: Despite the rapid progress, LLMs for sequential decision-making (i.e., LLM agents) still struggle to produce diverse outputs. This leads to insufficient
arXiv:2604.16979v1 Announce Type: cross Abstract: High-quality and diverse multimodal data are essential for improving vision-language models (VLMs), yet existing datasets often contain noisy, redunda
arXiv:2510.00761v5 Announce Type: replace Abstract: Large language model (LLM) unlearning aims to surgically remove the influence of undesired data or knowledge from an existing model while preserving
arXiv:2506.12622v2 Announce Type: replace Abstract: Deep reinforcement learning (RL) has achieved remarkable success, yet its deployment in real-world scenarios is often limited by vulnerability to en
arXiv:2604.17209v1 Announce Type: new Abstract: Automating medical reports for retinal images requires a sophisticated blend of visual pattern recognition and deep clinical knowledge. Current Large Vi
arXiv:2604.17195v1 Announce Type: new Abstract: Storyboard synthesis plays a crucial role in visual storytelling, aiming to generate coherent shot sequences that visually narrate cinematic events with
arXiv:2507.20879v3 Announce Type: replace Abstract: The advent of Vision-Language Models (VLMs) has significantly advanced end-to-end autonomous driving, demonstrating powerful reasoning abilities for
arXiv:2512.16055v2 Announce Type: replace Abstract: Safety-critical corner cases, difficult to collect in the real world, are crucial for evaluating end-to-end autonomous driving. Adversarial interact
arXiv:2604.17841v1 Announce Type: new Abstract: Most autonomous driving safety benchmarks use time-to-collision (TTC) to assess risk and guide safe behaviour. However, TTC-based methods treat risk as
arXiv:2604.18368v1 Announce Type: new Abstract: A key challenge in segmentation in digital histopathology is inter- and intra-stain variations as it reduces model performance. Labelling each stain is
arXiv:2603.08090v2 Announce Type: replace Abstract: Significant progress has been achieved in subject-driven text-to-image (T2I) generation, which aims to synthesize new images depicting target subjec
arXiv:2604.18563v1 Announce Type: new Abstract: A recent study (Kuribayashi et al., 2025) has shown that human sentence processing behavior, typically measured on syntactically unchallenging construct
arXiv:2604.17473v1 Announce Type: new Abstract: Vision-Language Navigation(VLN) requires an agent to navigate through 3D environments by following natural language instructions. While recent Video Lar
arXiv:2602.10764v2 Announce Type: replace Abstract: The slow iterative sampling nature remains a major bottleneck for the practical deployment of diffusion and flow-based generative models. While cons
arXiv:2604.17542v1 Announce Type: new Abstract: Conventional test-time adaptation (TTA) approaches typically adapt the model using only a small fraction of test samples, often those with low-entropy p
arXiv:2604.17688v1 Announce Type: new Abstract: 3D human pose estimation is a classic and important research direction in the field of computer vision. In recent years, Transformer-based methods have
arXiv:2604.18540v1 Announce Type: cross Abstract: Adversarial training of binary classifiers can be reformulated as regularized risk minimization involving a nonlocal total variation. Building on this
arXiv:2503.14324v3 Announce Type: replace-cross Abstract: The differing representation spaces required for visual understanding and generation pose a challenge in unifying them within the autoregressi
arXiv:2604.17411v1 Announce Type: new Abstract: Text-attributed graphs integrate semantic information of node texts with topological structure, offering significant value in various applications such
arXiv:2604.17789v1 Announce Type: cross Abstract: The MXFP4 microscaling format, which partitions tensors into blocks of 32 elements sharing an E8M0 scaling factor, has emerged as a promising substrat
arXiv:2604.16987v1 Announce Type: new Abstract: The rapid evolution of video generation technologies poses a significant challenge to media forensics, as conventional detection methods often fail to g
arXiv:2604.17037v1 Announce Type: new Abstract: Deception detection is of great significance for ensuring information security and conducting public opinion analysis, with personality factors and emot
arXiv:2604.16483v1 Announce Type: new Abstract: Concept erasure in Text-To-Image (T2I) diffusion models is vital for safe content generation, but existing inference-time methods face significant limit