Knowledge catalogue
arXiv:2604.23069v1 Announce Type: new Abstract: Large language model (LLM) agents often struggle in long-context interactions. As the agent accumulates more interaction history, context management app
arXiv:2604.23987v1 Announce Type: new Abstract: Continual learning for large language models is typically evaluated through accuracy retention under sequential fine-tuning. We argue that this perspect
arXiv:2604.24637v1 Announce Type: cross Abstract: Block-sequential continual learning demands that a single model both protect prior solutions from catastrophic forgetting and efficiently infer at inf
arXiv:2508.13650v3 Announce Type: replace Abstract: As large language models (LLMs) are increasingly deployed in real-world applications, the need to selectively remove unwanted knowledge while preser
arXiv:2510.17687v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) achieve strong reasoning and perception capabilities but are increasingly vulnerable to jailbreak att
arXiv:2604.23214v1 Announce Type: new Abstract: Memes convey meaning through the interaction of visual and textual signals, often combining humor, irony, and offense in subtle ways. Detecting harmful
arXiv:2604.23054v1 Announce Type: cross Abstract: Predicting the outcomes of prospective clinical trials remains a major challenge for large language models. Prior work has shown that both traditional
arXiv:2604.24029v1 Announce Type: cross Abstract: Identifying species in biology among tens of thousands of visually similar taxa while discovering unknown species in open-world environments remains a
arXiv:2601.02455v2 Announce Type: replace-cross Abstract: Deploying Automatic Speech Recognition (ASR) models on memory-constrained edge devices requires aggressive low-bit weight quantization. Layer-
arXiv:2604.24575v1 Announce Type: new Abstract: Diffusion models are primarily trained for image synthesis, yet their denoising trajectories encode rich, spatially aligned visual priors. In this paper
arXiv:2604.23557v1 Announce Type: cross Abstract: Building scalable and reusable multi-agent decision policies from offline datasets remains a challenge in offline multi-agent reinforcement learning (
arXiv:2604.23385v1 Announce Type: new Abstract: Transthoracic echocardiography is the reference standard for confirming structural heart disease (SHD), but first-line screening is limited by cost, wor
arXiv:2604.23801v1 Announce Type: new Abstract: Practitioners deploying small open-weight large language models (LLMs) for medical question answering face a recurring design choice: invest in a domain
arXiv:2509.06027v3 Announce Type: replace-cross Abstract: With the development of large-scale diffusion-based and language-modeling-based generative models, impressive progress has been achieved in te
arXiv:2510.15050v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) have made rapid progress, yet their reasoning ability often lags behind strong text-only LLMs. Bridging thi
arXiv:2604.24426v1 Announce Type: new Abstract: AI-generated media are advancing rapidly, raising pressing concerns for content authenticity and digital trust. We introduce DYMAPIA, a multi-domain Dee
arXiv:2203.04153v2 Announce Type: replace Abstract: Sensor-based human activity recognition (HAR) is a paramount technology in the Internet of Things services. HAR using representation learning, which
arXiv:2603.10926v1 Announce Type: cross Abstract: Time-series anomaly detectors are commonly compared on workstation-class hardware under unconstrained execution. In-vehicle monitoring, however, requi
arXiv:2604.23763v1 Announce Type: new Abstract: Large diffusion transformers (DiTs) follow global editing instructions well but consistently leak local edits into unrelated regions, because joint-atte
arXiv:2604.23336v1 Announce Type: cross Abstract: Unlike traditional fact-based retrieval, rationale-based retrieval typically necessitates cross-encoding of query-document pairs using large language
arXiv:2604.22851v1 Announce Type: cross Abstract: While Vision-Language Models (VLMs) have advanced highlevel reasoning in autonomous driving, their ability to ground this reasoning in the underlying
arXiv:2604.23798v1 Announce Type: cross Abstract: Existing attention accelerators often trade exact softmax semantics, depend on fused Tensor Core kernels, or incur sequential depth that limits FP32 t
arXiv:2508.21094v3 Announce Type: replace Abstract: Video-LLMs face a fundamental tension in long-video reasoning: static, sparse frame sampling either dilutes evidence across task-irrelevant segments
arXiv:2604.23861v1 Announce Type: cross Abstract: Convolutional neural networks (CNNs) remain a central approach in image classification, but their performance depends strongly on architectural and tr
arXiv:2604.24041v1 Announce Type: cross Abstract: Partially-observed time series (POTS) is ubiquitous in real-world applications, yet most existing toolchains separate missing-value handling from down
arXiv:2604.23472v1 Announce Type: new Abstract: While recent autonomous agents demonstrate impressive capabilities, they predominantly rely on manually scripted workflows and handcrafted heuristics, i
arXiv:2604.23728v1 Announce Type: cross Abstract: Recent advances in autonomous driving have motivated research on pedestrian intention prediction, which aims to infer future crossing decisions and ac
arXiv:2604.23466v1 Announce Type: cross Abstract: NVIDIA's CUDA Tile (CuTile) introduces a Python-based, tile-centric abstraction for GPU kernel development that aims to simplify programming while ret
arXiv:2604.23051v1 Announce Type: new Abstract: Language models are increasingly deployed in interactive settings where users reason about facts over time rather than in isolation. In such scenarios,
arXiv:2604.22842v1 Announce Type: new Abstract: Face Image Quality Assessment is crucial for reliable face recognition systems, yet existing Vision Transformer-based approaches rely exclusively on fin
arXiv:2604.23344v1 Announce Type: new Abstract: Conventional object detectors typically operate under a closed-set assumption, limiting recognition to a predefined set of base classes seen during trai
arXiv:2506.12382v5 Announce Type: replace-cross Abstract: Ensuring the safety and alignment of Large Language Models is a significant challenge with their growing integration into critical application
arXiv:2603.21768v3 Announce Type: replace-cross Abstract: Precipitation nowcasting is critical for disaster mitigation and aviation safety. However, radar-only models frequently suffer from a lack of
arXiv:2604.22885v1 Announce Type: cross Abstract: Federated cross-modal retrieval faces severe challenges from heterogeneous client data, particularly non-IID semantic distributions and missing modali
arXiv:2604.24397v1 Announce Type: cross Abstract: In the noisy intermediate-scale quantum (NISQ) regime, quantum devices contain hardware-specific noise sources which restrict device-invariant error m
arXiv:2604.23989v1 Announce Type: cross Abstract: Recent work on large language models (LLMs) has emphasized the importance of scaling inference compute. From this perspective, the state-of-the-art me
arXiv:2604.23658v1 Announce Type: cross Abstract: Chip placement plays an important role in physical design. While generative models like diffusion models offer promising learning-based solutions, cur
arXiv:2602.12120v3 Announce Type: replace Abstract: Effective resource allocation in higher education depends on reliable enrolment forecasts, yet institutional planners frequently face data series di
arXiv:2604.23002v1 Announce Type: new Abstract: Formalising informal mathematical reasoning into formally verifiable code is a significant challenge for large language models. In scientific fields suc
arXiv:2507.14137v4 Announce Type: replace Abstract: We present Franca (pronounced Fran-ka): free one; the first fully open-source (data, code, weights) vision foundation model that matches and in many
arXiv:2604.23079v1 Announce Type: cross Abstract: The quality of diabetic retinopathy (DR) screening relies on the ability to correctly grade severity; however, many deep-learning (DL) classifiers can
arXiv:2604.23277v1 Announce Type: cross Abstract: Long-context large language models remain computationally expensive to run and often fail to reliably process very long inputs, which makes context co
arXiv:2604.23338v1 Announce Type: cross Abstract: Agentic AI systems face security challenges that stateless large language models do not. They plan across extended horizons, maintain persistent memor
arXiv:2604.05621v2 Announce Type: replace Abstract: We present FunRec, a method for reconstructing functional 3D digital twins of indoor scenes directly from egocentric RGB-D interaction videos. Unlik
arXiv:2511.22125v2 Announce Type: replace Abstract: Visual and textual soft prompt tuning can effectively improve the adaptability of Vision-Language Models (VLMs) in downstream tasks. However, fine-t
arXiv:2603.17834v2 Announce Type: replace-cross Abstract: Diffusion models and flow matching have become a cornerstone of robotic imitation learning, yet they suffer from a structural inefficiency whe
arXiv:2604.24396v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) are frequently undermined by object hallucination--generating content that contradicts visual reality--due to an over-re
arXiv:2604.23941v1 Announce Type: new Abstract: Graphical User Interface (GUI) element grounding (precisely locating elements on screenshots based on natural language instructions) is fundamental for
arXiv:2604.24234v1 Announce Type: new Abstract: The technological maturity of in situ inspection and monitoring methods in additive manufacturing is steadily increasing, enabling more efficient and pr
arXiv:2512.05359v2 Announce Type: replace Abstract: Parameter-efficient fine-tuning has emerged as a promising paradigm in RGB-T tracking, enabling downstream task adaptation by freezing pretrained pa
arXiv:2604.24551v1 Announce Type: cross Abstract: Quantum error mitigation (QEM) is essential for extracting reliable results from near-term quantum devices, yet practical deployments must balance mit
arXiv:2506.04118v3 Announce Type: replace Abstract: We propose Guided Speculative Inference (GSI), a novel algorithm for efficient reward-guided decoding in large language models. GSI combines soft be
arXiv:2604.23606v1 Announce Type: new Abstract: Lattice Hamiltonian systems underpin models across condensed matter, nonlinear optics, and biophysics, yet learning their dynamics from data is obstruct
arXiv:2604.23717v1 Announce Type: cross Abstract: Recent large audio language models (LALMs) demonstrate remarkable capabilities in processing extended multi-modal sequences, yet incur high inference
arXiv:2603.17573v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) Models have become the mainstream solution for robot control, but suffer from slow inference speeds. Speculative
.@huggingface unveiled ml-intern – an open-source agent that automates the gritty post-training loop: - reading papers - tracing citations - curating datasets - running experiments - and iterating lik
arXiv:2604.24040v1 Announce Type: cross Abstract: Transformer-based table retrieval systems flatten structured tables into token sequences, making retrieval sensitive to the choice of serialization ev
arXiv:2604.24583v1 Announce Type: new Abstract: Recent advancements in reinforcement learning with verifiable rewards (RLVR) have significantly improved the complex reasoning ability of vision-languag
arXiv:2602.12971v2 Announce Type: replace Abstract: Driven by recent advancements in foundation models, semantic scene graphs have emerged as a promising paradigm for high-level 3D environmental abstr
arXiv:2508.19679v2 Announce Type: replace Abstract: Recent advances in Vision-Language Models (VLMs) have enabled mobile agents to perceive and interact with real-world mobile environments based on hu