Knowledge catalogue
arXiv:2608.29078v1 Announce Type: new Abstract: Vision-language-action (VLA) models have made strong progress in language-conditioned robot manipulation, but improving their performance in a new works
arXiv:2608.28730v1 Announce Type: cross Abstract: Latest JPEG restoration systems achieve strong quality with large models, yet often remain too slow and expensive for efficient on-device deployment.
arXiv:2608.29126v1 Announce Type: new Abstract: Referring single-object tracking enables language-grounded target initialization and subsequent tracking by jointly leveraging semantic cues and visual
arXiv:2608.29281v1 Announce Type: new Abstract: Natural images concentrate their detail in a small fraction of the frame, yet diffusion models spend a full token on every patch, in every layer and at
arXiv:2608.30462v1 Announce Type: cross Abstract: Large language models exhibit substantial performance variation across languages, even when solving semantically equivalent tasks. Existing analyses o
arXiv:2608.29802v1 Announce Type: new Abstract: Face recognition systems are increasingly deployed in security-critical applications, yet they remain vulnerable to presentation and morph attacks. Pres
arXiv:2608.30858v1 Announce Type: cross Abstract: Off-road navigation can fail when physical structures induce irrecoverable states such as high-centering or entrapment, requiring human interventions.
arXiv:2608.30550v1 Announce Type: new Abstract: Multimodal Sewing pattern generation aims to infer executable sewing patterns from design cues such as sketches and textual descriptions. As an interpre
arXiv:2608.29395v1 Announce Type: new Abstract: Vision-language models such as CLIP and SigLIP provide strong zero-shot recognition, but their predictions can degrade when deployed on target data that
arXiv:2608.29680v1 Announce Type: new Abstract: Feed-forward 3D foundation models reconstruct perspective scenes in one pass. Satellite photogrammetry needs a different product, one that domain adapta
arXiv:2608.30841v1 Announce Type: new Abstract: Large language models can often generate plausible mathematical reasoning traces, but reliably identifying the correct solution among multiple candidate
arXiv:2608.29207v1 Announce Type: new Abstract: Protein structure modeling rests on a single computational primitive: the interaction between what a residue is (sequence content) and where it sits (th
arXiv:2608.31053v1 Announce Type: new Abstract: Diffusion models have achieved strong results in high-fidelity image synthesis, but their iterative sampling process makes large-scale generation comput
arXiv:2508.15757v2 Announce Type: replace Abstract: Configuration optimization remains a critical bottleneck in machine learning, requiring coordinated tuning across model architecture, training strat
arXiv:2508.13073v3 Announce Type: replace-cross Abstract: Robotic manipulation, a key frontier in robotics and embodied AI, requires precise motor control and multimodal understanding, yet traditional
arXiv:2607.10851v2 Announce Type: replace Abstract: Medical image classification models are ideally expected to identify diagnostically relevant regions while making predictions, yet standard classifi
arXiv:2608.30773v1 Announce Type: new Abstract: In animals such as elephants and octopuses, acquiring non-visual information about an object and physically engaging with it are inseparable processes m
arXiv:2608.30935v1 Announce Type: cross Abstract: Embodied navigation requires agents to translate heterogeneous goals and visual observations into actions across tasks, environments, and robot embodi
arXiv:2601.07533v3 Announce Type: replace-cross Abstract: Tracing connections between historical texts is an important part of intertextual research, enabling scholars to reconstruct the virtual libra
arXiv:2608.30902v1 Announce Type: new Abstract: Adapting large language models to user-specific preferences is often constrained by the cost of human annotation, making preference optimisation impract
arXiv:2608.30114v1 Announce Type: new Abstract: Brazilian Portuguese remains under-served by open language models, and the few that exist are difficult to reproduce and are often compared without meas
arXiv:2608.28773v1 Announce Type: cross Abstract: Perceptual losses are widely used in medical image synthesis because they encourage agreement in high-level structure beyond voxel-wise intensity simi
arXiv:2608.30521v1 Announce Type: new Abstract: Conventional algebraic triangulation solves 3D human pose estimation (HPE) from multi-view 2D keypoints. The typical approach, decoding 2D keypoints fro
arXiv:2608.28933v1 Announce Type: new Abstract: Stereo reconstruction is one of the last remaining Computer Vision tasks where all state-of-the-art methods employ a heavy architectural inductive bias.
arXiv:2608.31036v1 Announce Type: new Abstract: While low-rank adaptation (LoRA) is widely used for parameter-efficient model adaptation, how to regularize its training dynamics for stable and effecti
arXiv:2608.30320v1 Announce Type: new Abstract: We describe the architecture and ablations of Qwen3.8-Flash-Next, a sparse mixture-of-experts model with 125B parameters, 6B activated per token, and ad
arXiv:2608.31096v1 Announce Type: new Abstract: Class-incremental learning (CIL) requires a model to incrementally learn tasks that contain new classes without accessing earlier training data while pr
arXiv:2603.03485v4 Announce Type: replace-cross Abstract: Recent video diffusion models have achieved impressive capabilities as large-scale generative world models. However, these models often strugg
arXiv:2608.30609v1 Announce Type: cross Abstract: Large language models are increasingly capable in general, but their utility can remain modest in niche or understudied areas. One approach to address
arXiv:2608.29109v1 Announce Type: new Abstract: Large language models often answer structurally unanswerable questions, such as computing cot(-540{eg}) or evaluating (1).startswith('1'), instead of ab
arXiv:2607.16325v2 Announce Type: replace Abstract: Foundation models provide powerful representations for brain MRI analysis, but their predictions remain difficult to interpret in anatomically meani
arXiv:2602.08136v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) are now a core part of modern AI. Recent work proposed several visual jailbreak attacks using single/ holistic i
arXiv:2608.30410v1 Announce Type: cross Abstract: In semiconductor manufacturing, defect analysis is essential, but manual inspection cannot scale. However, existing automated inspection methods remai
arXiv:2512.15052v4 Announce Type: replace-cross Abstract: Disclaimer: Samples in this paper may be harmful and cause discomfort. Multimodal large language models (MLLMs) enable multimodal understandin
arXiv:2608.29220v1 Announce Type: new Abstract: Multimodal image fusion (MMIF) aims to integrate complementary sensor data into a single representation that preserves intrinsic scene reality while eli
arXiv:2608.29364v1 Announce Type: new Abstract: Early-stage product design retrieval often requires more than category recognition: designers may need reference examples that match both a short semant
arXiv:2608.29162v1 Announce Type: cross Abstract: We describe the submission of team FME to the MAMA-MIA Challenge, which evaluated primary tumor segmentation and prediction of pathological complete r
Super interesting paper from Meta. Long-horizon research agents are coming. But one common problem with research agents today is the lack of originality and how to decide what experiments are worth ex
arXiv:2608.29759v1 Announce Type: cross Abstract: We present SynCrash, a multi-stage pipeline for zero-shot accident detection, spatial localization, and collision-type classification in fixed-view CC
arXiv:2608.30643v1 Announce Type: new Abstract: Recent vision-language-action (VLA) methods improve manipulation performance by aligning their representations with 3D scene geometry. However, these me
arXiv:2608.28980v1 Announce Type: cross Abstract: Can the specialized architectures that machine learning has traditionally built for structured data be replaced by language-based models? This questio
arXiv:2608.30720v1 Announce Type: new Abstract: Representational similarity is foundational to analyses of deep networks, yet distances between point-valued representations are not intrinsically tied
arXiv:2608.31013v1 Announce Type: cross Abstract: Designing models that generalize effectively in low- to medium-data regimes remains a primary challenge in medical machine learning, particularly for
arXiv:2608.29327v1 Announce Type: new Abstract: Large language models deployed in specialized domains must improve in-domain performance without sacrificing general capabilities. Existing parameter-ef
arXiv:2511.19145v4 Announce Type: replace Abstract: Low-Rank Adaptation (LoRA) is highly sensitive to initialization, yet existing schemes construct the initial subspace from statistics at the pretrai
arXiv:2608.28082v1 Announce Type: new Abstract: Autoregressive text-to-image generation has recently achieved remarkable progress, offering high-fidelity synthesis via a unified generative framework.
arXiv:2608.27817v1 Announce Type: cross Abstract: Speech and audio LLMs are often evaluated by asking whether a waveform prompt beats an automatic speech recognition (ASR) transcript. For known closed
arXiv:2608.27550v1 Announce Type: cross Abstract: Scaling robot data is crucial for building generalist Vision-Language-Action (VLA) models, yet robot trajectories are harder to scale than web-scale i
arXiv:2608.28478v1 Announce Type: new Abstract: Factual question answering (QA) typically assumes a single canonical answer, obscuring whether large language models (LLMs) retain divergent accounts of
arXiv:2506.04970v2 Announce Type: replace Abstract: Information on trees at the individual level is crucial for monitoring forest ecosystems and planning forest management. Current monitoring methods
arXiv:2508.21240v2 Announce Type: replace Abstract: This work introduces a novel generative continual learning framework based on self-organizing maps (SOMs), a brain-inspired natural computing model,
arXiv:2608.28108v1 Announce Type: cross Abstract: Vision-Language-Action models (VLAs) allow users to specify manipulation tasks in natural language, but distinguishing a target or placement goal amon
arXiv:2608.28092v1 Announce Type: cross Abstract: Interpreting a CT scan means comparing structures on either side, judging how far apart organs sit, and knowing where each one belongs. Medical vision
arXiv:2608.28161v1 Announce Type: new Abstract: Mango variety identification in Bangladesh is challenging because closely related cultivars can have similar visual characteristics and images are often
arXiv:2608.28404v1 Announce Type: new Abstract: Video generation for autonomous driving cannot follow the web-scale route: driving data is expensive to collect, bound by privacy requirements, and cann
arXiv:2608.27791v1 Announce Type: new Abstract: Short-term load forecasting (STLF) provides essential information for numerous applications in modern power systems. However, accurate STLF often relies
arXiv:2511.23271v2 Announce Type: replace Abstract: Long system prompts are widely used to steer Large Language Models (LLMs), but repeatedly processing them at inference time is inefficient and consu
arXiv:2608.28517v1 Announce Type: new Abstract: Cross-modal image translation in remote sensing must preserve source-observed content while matching the target-domain distribution. Existing methods jo
arXiv:2608.27719v1 Announce Type: new Abstract: Biological heterogeneity in Alzheimer's Disease (AD) poses a critical diagnostic challenge, particularly for traditional linear methods that fail to cap
arXiv:2406.10221v3 Announce Type: replace-cross Abstract: Recent developments in vision-language models have significantly advanced video understanding. Existing datasets and tasks, however, have nota