Knowledge catalogue
arXiv:2609.08618v1 Announce Type: new Abstract: Benchmark scores describe what a checkpoint can do now, but they do not determine how it will respond to the next training episode. We measure this miss
arXiv:2609.08512v1 Announce Type: new Abstract: Autonomous exploration on uneven terrain requires ground robots to balance exploration efficiency, coverage completeness, and terrain safety. Detailed t
arXiv:2609.09025v1 Announce Type: new Abstract: State-of-the-art vision models process images in their entirety, lacking the ability to selectively zoom in on relevant regions. This limitation is part
arXiv:2609.06242v1 Announce Type: cross Abstract: Connected and automated vehicle platoons require reliable dissemination of task-relevant hazard information to enable appropriate downstream responses
arXiv:2609.08011v1 Announce Type: new Abstract: Image restoration is commonly applied before object detection under adverse conditions, yet a visually improved image need not improve the downstream ta
arXiv:2609.07444v1 Announce Type: new Abstract: The rise of privacy-preserving artificial intelligence (AI) has shifted the focus of model adaptation and personalization towards on-device learning, wh
arXiv:2609.06144v1 Announce Type: new Abstract: Visual dubbing must synchronize mouth motion with replacement speech while preserving identity, appearance, and temporal consistency. Although X-Dub pro
arXiv:2609.06636v1 Announce Type: cross Abstract: Fine-grained mobile traffic demand forecasting is essential for long-term planning of 5G and future 6G networks, including radio upgrades, site densif
arXiv:2609.07937v1 Announce Type: new Abstract: Structured visual reasoning, such as image puzzles, demands fine-grained visual perception, an ability current Vision Language Models (VLMs) lack. VLMs
Technology is only good if it empowers you. If it locks you down, saps your attention, or steals your ideas, then it should be discarded. LLMs could go either way. That's why we are dedicated to open,
arXiv:2609.07540v1 Announce Type: new Abstract: Contrastive learning approaches achieve strong performance by training models to bring similar samples closer while pushing dissimilar samples apart. A
arXiv:2406.15070v3 Announce Type: replace-cross Abstract: We present Tempora-Fusion, the first homomorphic TLP scheme with efficient public verification of both individual puzzle solutions and homomor
arXiv:2512.12427v3 Announce Type: replace Abstract: Many aerial tasks involving quadrotors demand both instant reactivity and long-horizon planning for obstacle avoidance, energy efficiency, or trajec
arXiv:2609.07461v1 Announce Type: new Abstract: We consider reinforcement learning in environments with dynamics that undergo an irreversible phase transition governed by a hidden temporal pattern. Th
arXiv:2603.02935v2 Announce Type: replace Abstract: Offline meta-reinforcement learning seeks to learn a policy that generalizes to new related tasks online. Context-based methods infer a task represe
arXiv:2609.07100v1 Announce Type: new Abstract: Credit card fraud detection typically relies on tabular features, while repeated attributes can also provide useful relational signals. This paper propo
arXiv:2601.02310v2 Announce Type: replace Abstract: High-Frequency trading (HFT) environments are characterised by large volumes of limit order book (LOB) data, which is notoriously noisy and non-line
arXiv:2609.08505v1 Announce Type: new Abstract: Reliable video generation requires more than high-quality frames to form a coherent story: a model must maintain a persistent state, transporting visual
arXiv:2609.07184v1 Announce Type: cross Abstract: We present tensor network representations for discrete maximum entropy distributions under expectation constraints. To this end, we introduce Computat
arXiv:2609.05968v1 Announce Type: new Abstract: Aligning a text-to-image generation flow model with a reward makes it follow objectives that the training data alone does not provide. Alignment fine-tu
arXiv:2602.13418v2 Announce Type: replace Abstract: Does natural language text have an intrinsic curvature? Language is increasingly modeled in curved geometries - hyperbolic spaces for hierarchy, mix
arXiv:2609.07738v1 Announce Type: new Abstract: LiDAR-based 3D Single Object Tracking (3D SOT) is critical for robotic perception and navigation and aims to localize dynamic objects across frames in s
arXiv:2609.07897v1 Announce Type: new Abstract: Automated prediction of Enzyme Commission (EC) numbers plays a central role in functional annotation and computational drug discovery. However, standard
arXiv:2609.07638v1 Announce Type: cross Abstract: Hyphenation patterns remain a compact and widely deployed solution for word breaking in typesetting systems, text processors, and web rendering engine
arXiv:2609.08901v1 Announce Type: new Abstract: Approximate machine unlearning aims to remove the influence of specific training data from a trained model without retraining from scratch. We identify
arXiv:2403.18767v4 Announce Type: replace-cross Abstract: In the classical best approximation pair (BAP) problem, one is given two nonempty, closed, convex and disjoint subsets in a finite- or an infi
Gary Marcus argues that current generative‑AI models fail to meet basic standards of reliability because they routinely hallucinate facts, amplify existing biases, and provide no transparent audit tra
arXiv:2504.16450v4 Announce Type: replace Abstract: We derive a differential equation that governs the evolution of the generalization gap when a model is trained by gradient descent-based methods. Th
arXiv:2409.09903v3 Announce Type: replace-cross Abstract: Softmax Mixture Models (SMMs) are discrete K-component mixture models for the probabilities of selecting one of p candidate feature vectors X_
arXiv:2609.08537v1 Announce Type: cross Abstract: We study the time-uniform convergence of the raw iterate of standard stochastic gradient descent (SGD) for unconstrained smooth convex objectives. We
The frontier labs are knowingly and by their own admission doing something irreversible and dangerous without public consent. They are already causing harms, and things could conceivably get much wors
arXiv:2609.06934v1 Announce Type: new Abstract: Post-hoc safety training (RLHF, DPO) is the dominant way to align large language models, yet jailbreaks (Zou et al., 2023b), fine-tuning attacks (Qi et
the issue here is not that current or near-future machines are somehow “too smart”; it’s that they are too unreliable, and hence not worthy of our trust...we are rapidly giving such machines too much
Hi, I have the biggest pro subscription.. had it for months.. been using more or less the same models (GLM 5.x) - i would averagely be at 95% on a sunday.. and it would renew at Monday. Now we are att
arXiv:2609.07843v1 Announce Type: cross Abstract: Machine learning has shown its largest gains in the band below 10 ms inside a 3GPP new radio (NR) 5G distributed unit (DU): link adaptation, per-slot
arXiv:2609.07162v1 Announce Type: new Abstract: Several properties safety monitors are asked to certify, among them cross-tenant noninterference, sandbagging and evaluation awareness, are 2-safety hyp
arXiv:2609.07216v1 Announce Type: new Abstract: The rapid evolution of video generation has shifted the paradigm from pure text-driven to multi-conditional controllable generation, with reference imag
arXiv:2509.01809v2 Announce Type: replace-cross Abstract: We consider the problem of support recovery for sparse binary signals from noisy linear measurements. For sparse Gaussian measurement matrices
arXiv:2609.07959v1 Announce Type: cross Abstract: Machine learning models are widely used in clinical applications, social media, law enforcement and critical infrastructure. Verifying whether their o
arXiv:2603.25579v2 Announce Type: replace-cross Abstract: A key capability of modern neural networks is their capacity to simultaneously learn underlying rules and memorize specific facts or exception
The same people that are building the most advanced AI models and agents are those that are calling them alien, and state that they do not know how to reach alignment with AI. It might be possible tha
there is a difference between 'i am ok with models being trained on my data and released publicly later' and 'i am ok with internal models trained on my very recent efforts, being used to race the sol
There is a nice visualization of how task bundles change with AI & some good interactive simulations of GDP growth under different assumptions in this. But missing are the right policy responses if we
arXiv:2609.07406v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning improves the reasoning ability of large language models by introducing intermediate computation, but explicit rationale
arXiv:2609.06475v1 Announce Type: new Abstract: Large vision-language models (LVLMs) have recently achieved remarkable progress in general-purpose video understanding. However, their application to su
arXiv:2609.09075v1 Announce Type: new Abstract: In reinforcement learning with verifiable rewards (RLVR) trained with group relative policy optimization (GRPO), the KL-free reward-advantage term studi
This is a really neat benchmark. It's super interesting that Astra starts strong and holds the lead for up to 19 hours, but Fable 5.1 catches up in the final hours. Not entirely clear why. Different m
arXiv:2609.05718v1 Announce Type: cross Abstract: We study state tomography when each measurement acts on at most k fresh copies and no quantum memory is retained between blocks. We prove a lower boun
arXiv:2609.05596v1 Announce Type: new Abstract: Can interactive vision-and-language agents learn not just what to say but also extbf{extit{when}} to say it? Current language models rarely plan over wh
arXiv:2602.00288v4 Announce Type: replace Abstract: Fine-grained spatio-temporal understanding is essential for video reasoning and embodied AI. Yet, while Multimodal Large Language Models (MLLMs) mas
arXiv:2603.04949v2 Announce Type: replace-cross Abstract: As web agents close the gap with humans on benchmarks, one question arises: Do today's agents perform just as well on tomorrow's web? We intro
arXiv:2609.08367v1 Announce Type: new Abstract: Test-time adaptation (TTA) has emerged as a prominent strategy for adapting vision-language models to distribution shifts during inference. We conduct a
arXiv:2609.08703v1 Announce Type: cross Abstract: Text-to-speech systems often face a trade-off between natural prosody and efficient inference: higher perceptual quality typically comes at increased
arXiv:2609.08445v1 Announce Type: new Abstract: Working entirely on topologically anonymized embeddings, we perform fraud detection using iterative rounds of unsupervised filtering followed by supervi
arXiv:2609.07520v1 Announce Type: new Abstract: Agricultural parcel polygons play a fundamental role in geospatial applications such as precision agriculture, land administration, and crop monitoring.
arXiv:2609.08152v1 Announce Type: new Abstract: Graph representation learning has largely focused on designing increasingly sophisticated models to transform graph topology into vector representations
arXiv:2505.04376v2 Announce Type: replace-cross Abstract: LiDAR-based perception plays a fundamental role in modern robotic systems for environment understanding and navigation. Single-photon LiDAR (S
arXiv:2609.05565v1 Announce Type: cross Abstract: Large language model (LLM) sustainability is increasingly a serving-systems problem, not only a training problem. In production, energy and carbon imp
arXiv:2609.06893v1 Announce Type: cross Abstract: Direct preference optimization DPO is a promising offline approach for aligning large language models (LLMs) due to its simplicity, computational effi
arXiv:2609.08402v1 Announce Type: new Abstract: Air-Ground Object Search (AGOS) in urban environments is a challenging embodied task, which requires an Unmanned Aerial Vehicle (UAV) and an Unmanned Gr