Knowledge catalogue
arXiv:2605.21919v1 Announce Type: new Abstract: Assessing progress toward the Sustainable Development Goals (SDGs) requires multi-step reasoning over visual cues, contextual knowledge, and development
arXiv:2605.22633v1 Announce Type: new Abstract: The Python robotics ecosystem faces a challenge: while many libraries exist for rigid body transformations, few are both lightweight and mathematically
arXiv:2605.22511v1 Announce Type: cross Abstract: Post-training has become the dominant recipe for turning a language model into a competent search-augmented reasoning agent. A line of recent work pus
arXiv:2605.20368v1 Announce Type: cross Abstract: Organizations that scan documents for sensitive information face a practical problem. Cloud services require data to be sent to external infrastructur
arXiv:2605.22654v1 Announce Type: new Abstract: Previous detection studies have shown that LLMs cannot be effectively used as detectors, but these studies have not addressed modern Chinese poetry. Mor
arXiv:2605.22668v1 Announce Type: new Abstract: Diffusion transformers (DiTs) have emerged as a dominant architecture for text-to-image generation, yet their performance drops when generating at resol
arXiv:2605.22658v1 Announce Type: new Abstract: While large language models provide strong compositional reasoning, existing reasoning segmentation pipelines fail to transparently connect this reasoni
arXiv:2605.22572v1 Announce Type: new Abstract: Accurate segmentation of brain tumour sub-regions from multi-parametric MRI is critical for treatment planning yet remains challenging due to morphologi
arXiv:2605.22538v1 Announce Type: new Abstract: Traditional visual object tracking (VOT) methods typically rely on task-specific supervised training, limiting their generalization to unseen objects an
arXiv:2605.21852v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in general video understanding, their capacity to interpret invo
arXiv:2605.22675v1 Announce Type: new Abstract: Self-distillation bootstraps large language models (LLMs) by training on their own generations. However, existing methods either rely on external signal
arXiv:2605.21713v1 Announce Type: new Abstract: How can we distinguish whether a peer review was written by a human or generated by an AI model? We argue that, in this setting, authorship should not b
arXiv:2506.14648v2 Announce Type: replace Abstract: Preference-based Reinforcement Learning (PbRL) methods provide a solution to avoid reward engineering by learning reward models based on human prefe
arXiv:2605.22809v1 Announce Type: new Abstract: Robust training and validation of Autonomous Driving Systems (ADS) require massive, diverse datasets. Proprietary data collected by Autonomous Vehicle (
arXiv:2509.17086v2 Announce Type: replace Abstract: Detecting and localizing poultry is essential for advancing smart poultry farming. Despite the progress of detection-centric methods, challenges per
arXiv:2602.08064v2 Announce Type: replace-cross Abstract: The long-standing tension between Pre- and Post-Norm remains an open problem in Transformer architecture, reflecting a fundamental trade-off b
arXiv:2602.23231v2 Announce Type: replace Abstract: Human action recognition plays an important role when developing intelligent interactions between humans and machines. While there is a lot of activ
arXiv:2605.22677v1 Announce Type: new Abstract: Deploying vision models across devices with varying resource constraints, or even on a single device where available compute fluctuates due to battery s
arXiv:2605.22031v1 Announce Type: new Abstract: Accelerated MRI reconstruction requires recovering missing details while preserving anatomically coherent structures across large spatial regions. State
arXiv:2511.07820v3 Announce Type: replace-cross Abstract: Despite the rise of billion-parameter foundation models trained across thousands of GPUs, similar scaling gains have not been shown for humano
arXiv:2605.22536v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have made rapid progress in spatial intelligence, yet existing spatial reasoning benchmarks largely assume pr
arXiv:2512.10719v2 Announce Type: replace Abstract: End-to-end autonomous driving methods built on vision language models (VLMs) have undergone rapid development driven by their universal visual under
arXiv:2605.22283v1 Announce Type: new Abstract: We introduce SOMA, the Spatial Memory framework for Out-of-Vision Manipulation in Vision-Language-Action (VLA) models. Most existing VLAs implicitly ass
arXiv:2605.21965v1 Announce Type: new Abstract: Large language models increasingly use external tools such as web search and document retrieval to solve information-intensive tasks. However, multi-hop
arXiv:2605.22751v1 Announce Type: new Abstract: As generative image models evolve rapidly, the perceptual gap between generated and real images continues to narrow, making AI-generated image detection
arXiv:2603.08403v3 Announce Type: replace Abstract: Long-horizon action-conditioned video generation aims to synthesize temporally coherent videos that follow complex action instructions over extended
arXiv:2605.22158v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) face significant computational overhead when processing long videos due to the massive number of visual token
arXiv:2605.21800v1 Announce Type: cross Abstract: World models are central to building agents that can reason, plan, and generalize beyond their training data. However, research on world models is cur
arXiv:2605.21405v1 Announce Type: cross Abstract: Third-party Python libraries introduce dependency management overhead, supply chain risk, and deployment friction in constrained environments. A natur
arXiv:2605.22456v1 Announce Type: new Abstract: Cloud-hosted LLM driver agents provide useful semantic judgments, but their inference latency exceeds stepwise vehicle-control windows. Learned world mo
arXiv:2507.03674v3 Announce Type: replace Abstract: Extracting structured information from scientific literature is critical for accelerating discovery, yet Large Language Models (LLMs) often struggle
arXiv:2601.20107v2 Announce Type: replace-cross Abstract: Recent Vision-Language Models (e.g., ColPali) enable fine-grained Visual Document Retrieval (VDR) but incur prohibitive multi-vector index sto
arXiv:2605.22202v1 Announce Type: new Abstract: In this paper, we show that high-performing embedding models organize their embedding spaces in a consistent way. We evaluate 25 contemporary embedding
arXiv:2605.22476v1 Announce Type: cross Abstract: Entity tracking requires maintaining and updating latent states for entities and attributes over long sequences. Recent task-specific attention operat
arXiv:2511.04106v5 Announce Type: replace-cross Abstract: The diffusion of ideas and language in society has conventionally been described by S-shaped models, such as the logistic curve. However, the
arXiv:2605.22748v1 Announce Type: new Abstract: Autonomous systems have achieved superhuman performance in isolation or simulation, yet they remain brittle in shared, dynamic real-world spaces. This f
arXiv:2605.22484v1 Announce Type: new Abstract: Vision-Language Models (VLMs) excel at tasks like zero-shot classification and cross-modal retrieval by mapping images and text to a shared space, but t
arXiv:2605.21198v1 Announce Type: cross Abstract: Public events on social media generate large volumes of discussion whose collective dynamics carry direct value for opinion forecasting and crisis res
arXiv:2605.22217v1 Announce Type: cross Abstract: Self-play reinforcement learning trains language models on their own generated tasks, co-evolving a proposer and solver without human labels. Recent s
arXiv:2605.22678v1 Announce Type: new Abstract: While most frames in long-form video are redundant, the critical information resides in temporal surprises: moments where the actual visual features dev
arXiv:2605.22639v1 Announce Type: new Abstract: Robots exhibit a rich variety of symmetries arising from their mechanical structure and the properties of their tasks. Although many robotics problems e
arXiv:2605.22564v1 Announce Type: new Abstract: Today, tool-calling agents are commonly evaluated or tested on static datasets of execution traces, including input commands, agent responses, and assoc
arXiv:2605.22767v1 Announce Type: new Abstract: Children with rare genetic diseases often exhibit distinctive facial phenotypes, yet developing computer vision systems for early diagnosis remains chal
arXiv:2605.21523v1 Announce Type: cross Abstract: Steganalysis models excel on benchmark datasets but struggle in the wild when analyzed images are produced by a processing pipeline unseen during trai
arXiv:2605.21976v1 Announce Type: new Abstract: Vision-based learning from demonstrations has achieved remarkable success in enabling robots to perform manipulation tasks and high-level semantic reaso
arXiv:2605.20328v1 Announce Type: cross Abstract: Optimization problems such as the NP-complete 3-SAT provide an important benchmark for the difficult task of finding ground-states in strongly correla
arXiv:2605.21413v2 Announce Type: new Abstract: As AI becomes part of everyday learning, many courses teach students to use it mainly as a productivity tool: how to prompt, search, summarize, write, c
arXiv:2605.21491v1 Announce Type: cross Abstract: As language models accelerate scientific research by automating hypothesis generation and implementation, a new bottleneck emerges: evaluating and fil
arXiv:2605.22206v1 Announce Type: cross Abstract: The Thousand Brains Theory (TBT) and its open-source Monty framework model object recognition through sensorimotor inference -- identifying objects by
arXiv:2605.22443v1 Announce Type: new Abstract: Image-Based Visual Servoing (IBVS) provides an efficient vision-guided control paradigm for unmanned aerial vehicles (UAVs) by directly regulating image
arXiv:2605.22098v1 Announce Type: new Abstract: The platonic representation hypothesis suggests that sufficiently large models converge to a shared representation geometry, even across modalities. Mot
arXiv:2605.22635v1 Announce Type: cross Abstract: While multi-task learning based automatic radiology report generation (RRG) is widely adopted to ensure clinical consistency, most focus on architectu
arXiv:2605.22417v1 Announce Type: new Abstract: We observe that existing model interpretation methods generally ignore the baseline, and such neglect often results in imprecise or even incorrect inter
arXiv:2605.21882v1 Announce Type: new Abstract: Vision-language models (VLMs) often fail under low illumination because their visual grounding is learned predominantly from RGB imagery, whereas therma
arXiv:2605.22425v1 Announce Type: cross Abstract: Remote photoplethysmography (rPPG) enables non-contact measurement of cardiac pulse signals by analyzing subtle color changes in facial videos. Nevert
arXiv:2601.05106v4 Announce Type: replace-cross Abstract: Large language models (LLMs) exhibit strengths across diverse domains. However, achieving strong performance across these domains with a singl
arXiv:2605.21883v1 Announce Type: new Abstract: Direct Preference Optimization (DPO) aligns Large Language Models with human preferences without the need for a separate reward model. However, DPO trea
arXiv:2605.22821v1 Announce Type: new Abstract: Tokenisation is an integral part of the current NLP pipeline. Current tokenisation algorithms such as BPE and Unigram are greedy algorithms -- they make
arXiv:2605.22705v1 Announce Type: new Abstract: We introduce Tokenization with Split Trees (ToaST), a subword tokenization method that directly optimizes compression under a new recursive inference pr
arXiv:2605.20190v1 Announce Type: new Abstract: Iterative industrial design-simulation optimization is bottlenecked by the CAD-CAE semantic gap: translating simulation feedback into valid geometric ed