Knowledge catalogue
arXiv:2606.25782v1 Announce Type: new Abstract: With the widespread adoption of large language models (LLMs) in chatbots and everyday applications, companies increasingly need guardrails that are effe
arXiv:2606.25066v1 Announce Type: cross Abstract: Visual search has been one of the most productive paradigms in the study of visual attention: the way reaction time scales with the number of items di
arXiv:2606.25758v1 Announce Type: new Abstract: While test-time adaptation (TTA) empowers vision-language models to adapt without costly retraining, it remains highly vulnerable to out-of-distribution
arXiv:2606.25188v1 Announce Type: new Abstract: Efficient uncertainty quantification (UQ) is essential for trustworthy large-scale learning. Existing UQ methods for regression tasks mainly operate und
arXiv:2606.25354v1 Announce Type: new Abstract: Test-time scaling improves language-model reasoning, but existing approaches often face a difficult trade-off: long chain-of-thought sampling remains si
arXiv:2606.25732v1 Announce Type: new Abstract: Real-world single image dehazing is highly ill-posed due to spatially and spectrally varying scattering, while practical deployment demands lightweight
arXiv:2606.25324v1 Announce Type: new Abstract: The computational complexity of Transformers scales quadratically with the number of tokens, which significantly constrains the efficiency of vision mod
arXiv:2606.25176v1 Announce Type: new Abstract: We study representation learning for individual human chess style: a per-player embedding learned from a player's move history such that inner products
arXiv:2512.00804v3 Announce Type: replace-cross Abstract: When answering user queries, LLMs often retrieve knowledge from external sources stored in retrieval-augmented generation (RAG) databases. The
arXiv:2606.25177v1 Announce Type: new Abstract: Cognitive workload monitoring is important for adaptive rehabilitation and assistive interfaces, where task difficulty, pacing, and feedback should be a
arXiv:2603.09359v2 Announce Type: replace Abstract: Physics-informed neural networks (PINNs) have shown promise in addressing the ill-posed deconvolution problem in computed tomography perfusion (CTP)
arXiv:2606.25606v1 Announce Type: new Abstract: Given the widespread prevalence of depression and its consequential impact on individuals and society, it is crucial to obtain objective measures for ea
arXiv:2606.24994v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) for language-model reasoning can fail at both extremes of task difficulty: easy prompts often prod
arXiv:2606.25701v1 Announce Type: new Abstract: Conventional vision-language models are largely object-centric, focusing on detecting and describing individual entities. In safety-critical X-ray bagga
arXiv:2606.25585v1 Announce Type: new Abstract: Existing Referring Video Object Segmentation tasks focus on referring expressions describing events, actions or appearances of relevant objects within t
arXiv:2603.29591v2 Announce Type: replace Abstract: Every day, many people die under violent circumstances, whether from crimes, war, migration, or climate disasters. Medico-legal and law enforcement
arXiv:2606.25115v1 Announce Type: new Abstract: On-device language-model agents improve by accumulating experience in retrieved memory rather than by updating weights. This memory is hard-bounded and
arXiv:2502.18959v4 Announce Type: replace Abstract: The architecture of a neural network and the choice of its activation function are both fundamental to its performance. Equally important is ensurin
arXiv:2606.24969v1 Announce Type: new Abstract: While the quadratic sequence-length bottleneck of transformers has fueled a resurgence in recurrent models, effectively capturing complex dynamics requi
arXiv:2606.25460v1 Announce Type: cross Abstract: Recent advances in sequence modeling have significantly improved ASR systems, bringing them close to human-level recognition accuracy and enhancing ro
arXiv:2606.26017v1 Announce Type: new Abstract: In autonomous driving, diffusion-based planners have emerged as a promising paradigm for robust motion planning in dense and interactive traffic, as the
arXiv:2606.25808v1 Announce Type: cross Abstract: We propose a predict-optimize-explain framework that uses gradient-based sample generation to interpret various portfolio models by identifying macroe
arXiv:2505.13731v4 Announce Type: replace Abstract: Worldwide image geolocalization-the task of predicting GPS coordinates from images taken anywhere on Earth-poses a fundamental challenge due to the
arXiv:2603.14609v2 Announce Type: replace Abstract: Precise spatial understanding in Earth Observation is essential for translating raw aerial imagery into actionable insights for critical application
arXiv:2606.25404v1 Announce Type: new Abstract: Large Language Models (LLMs) can reason over complex instructions but often fail to satisfy the physical and spatial constraints required for robotic ta
arXiv:2606.25811v1 Announce Type: cross Abstract: Commodity futures can be represented hierarchically, with underlying assets at the upper level and individual futures contracts at the lower level. En
arXiv:2606.26002v1 Announce Type: new Abstract: We present HiReLC, a hierarchical ensemble-reinforcement learning framework for automated joint quantization and structured pruning of deep neural netwo
arXiv:2603.02156v2 Announce Type: replace-cross Abstract: Emerging 6G visions, reflected in ongoing standardization efforts within 3GPP, IETF, ETSI, ITU-T, and the O-RAN Alliance, increasingly charact
arXiv:2606.25338v1 Announce Type: new Abstract: Large language models (LLMs) have shown promising performance across a wide range of biomedical applications, including medical question answering (QA),
arXiv:2411.15490v2 Announce Type: replace Abstract: Acute ischemic stroke (AIS) requires time-critical decision-making, where inaccurate interpretation of neuroimaging findings can lead to irreversibl
arXiv:2604.25496v2 Announce Type: replace Abstract: Offline zero-shot reinforcement learning (RL) aims to learn agents that optimize unseen reward functions without additional environment interaction.
In a joint Fireworks and @Faros_AI evaluation of 211 real engineering tasks, Claude Code + GLM-5.2 beat both Claude Code + Opus 4.8 and Codex + GPT-5.5: - Judge score: 0.568 vs. 0.521 and 0.466 - Time
arXiv:2606.18394v2 Announce Type: replace Abstract: Speculative decoding (SD) accelerates autoregressive Large Language Models (LLMs) by drafting multiple tokens and verifying them in parallel, but it
Just had a great discussion on dynamic workflows. Rough notes: - applies to a very small set of use cases - think of it as a new paradigm of (test-time compute) TTC - strong for hill-climbing research
arXiv:2606.25169v1 Announce Type: cross Abstract: Sampling from an unnormalized target by reversing an Ornstein--Uhlenbeck diffusion requires the score of each noise-perturbed marginal. Tweedie's iden
arXiv:2606.25393v1 Announce Type: new Abstract: Hydropower tunnel inspection is critical for infrastructure integrity yet remains inefficient and hazardous using manual methods. We propose FLISP (Fast
arXiv:2606.24982v1 Announce Type: new Abstract: Modeling and sampling from the underlying distribution of asynchronous event sequences are crucial in various real-world applications, including social
arXiv:2606.25589v1 Announce Type: new Abstract: As graph neural networks (GNNs) become standard tools for critical tasks in circuit design and analysis, their security and privacy risks require carefu
arXiv:2606.25665v1 Announce Type: new Abstract: Domain generalization (DG) aims to learn a model from one or more source domains that generalizes to an unseen target domain without accessing target da
arXiv:2606.25451v1 Announce Type: new Abstract: Estimating token-level advantages in reinforcement learning (RL) for language models remains challenging because scaling up episodic experience collecti
arXiv:2606.25402v1 Announce Type: cross Abstract: Large software projects often depend on older versions of libraries, even as APIs continue to evolve across releases. This creates a challenge for LLM
arXiv:2606.25437v1 Announce Type: new Abstract: Existing Vision Foundation Model (VFM)-based iterative stereo pipelines under-exploit three information pathways: multi-scale backbone features are coll
arXiv:2606.24901v1 Announce Type: new Abstract: Continual learning capability is critical for Industrial LLMs, as deployed models must be continuously updated to meet evolving requirements and environ
arXiv:2606.25526v1 Announce Type: new Abstract: Cooperative multi-agent reinforcement learning assumes each agent shares the same reward function and can be trained effectively using the Trust Region
arXiv:2606.24815v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are emerging robotic control systems that integrate perception, language understanding, and action generation in a
arXiv:2606.25225v1 Announce Type: new Abstract: Self-supervised learning from large-scale video data has emerged as a dominant paradigm for visual representation learning. Since audio and visual strea
arXiv:2506.01486v2 Announce Type: replace Abstract: Data imbalance persists as a pervasive challenge in regression tasks, introducing bias in model performance and undermining predictive reliability.
arXiv:2606.17435v2 Announce Type: replace Abstract: Time-series forecasting models remain vulnerable to gradient-based adversarial attacks while existing defense mechanisms typically incur a trade-off
arXiv:2606.25978v1 Announce Type: cross Abstract: Multi-agent goal recognition asks an observer to jointly infer which agents act together and what each team is trying to achieve, so the hypothesis sp
arXiv:2606.26087v1 Announce Type: new Abstract: Synthesizing a novel-view video from a monocular reference video along a target camera trajectory requires both geometric consistency and motion fidelit
arXiv:2606.26080v1 Announce Type: new Abstract: Process reward models enable fine-grained, step-level evaluation of LLMs, yet building them for agentic settings remains prohibitively difficult: long-h
arXiv:2606.25389v1 Announce Type: new Abstract: Extracting skills from multi-agent offline dataset improves learning efficiency via sharing task-invariant coordination skills among tasks. In settings
arXiv:2606.25325v1 Announce Type: new Abstract: We find that current emotion-oriented Omni-MLLMs still lack reliable omni-modal perception: they (i) underutilize multimodal cues in their reasoning tra
arXiv:2606.24900v1 Announce Type: new Abstract: This paper proposes a new approach to near-sensor computing, in which a lightweight Neural Architecture Search (NAS) is performed directly on the deploy
arXiv:2606.26091v1 Announce Type: new Abstract: On-policy self-distillation achieves strong pass@1 accuracy by using a single model as both teacher and student, with the teacher conditioned on a corre
Open + closed models = better together. Our previous research with @harvey showed the benefits of combining a frontier closed model as an advisor agent with fine-tuned, open-source worker agents. Thre
arXiv:2606.15053v2 Announce Type: replace Abstract: Surrogate models are central to scientific machine learning, where they enable fast prediction, simulation, inference, and control for complex physi
arXiv:2606.25306v1 Announce Type: new Abstract: Video generation models are increasingly capable of producing realistic videos, but they still struggle to generate videos that follow basic physical la
arXiv:2606.25256v1 Announce Type: new Abstract: We introduce Pre-Warm, a simple yet effective zero-training-cost method for data-conditioned initialization of the first convolutional layer. Before the
arXiv:2606.25430v1 Announce Type: new Abstract: Reconstructing 3D scenes from a single image is a fundamental challenge in computer vision, with broad applications in virtual reality, robotics, and co