Knowledge catalogue
arXiv:2609.35507v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable advances in remote sensing. However, existing remote sensing multimodal reasoning
arXiv:2402.05071v3 Announce Type: replace-cross Abstract: We focus on constrained, L-smooth, potentially stochastic and nonconvex-nonconcave min-max problems either satisfying rho-cohypomonotonicity o
arXiv:2609.35562v1 Announce Type: new Abstract: This paper is a Track 2 reproducibility companion to an ICPR 2026 study on risky tackle detection in American football prac- tice videos. The original w
arXiv:2609.34310v1 Announce Type: new Abstract: K-means is a widely adopted clustering approach in signal processing and machine learning. In this paper, we study K-means clustering through a cardinal
Israeli identity security startup Rig Security Inc. launched today with 12 million in new funding to help enterprises keep watch over the artificial intelligence agents that operate under their employ
arXiv:2609.32537v1 Announce Type: new Abstract: Spiking-Mamba hybrids reach strong accuracy on event-based vision, but existing designs often require tens of millions of parameters. Much of that cost
arXiv:2609.34210v1 Announce Type: new Abstract: Coding agents are beginning to move beyond purely digital tasks to tackle physical-world challenges, particularly in robotics. Existing robotics benchma
arXiv:2609.34968v1 Announce Type: new Abstract: Vision-language-action and world-action models are increasingly popular, yet remain bottlenecked by physical interaction data that is scarce, institutio
arXiv:2609.32862v1 Announce Type: new Abstract: A foundation model should not act in isolation as an embodied agent. Yet, existing methods often optimize individual components of the agent stack, such
arXiv:2609.34261v1 Announce Type: cross Abstract: General-purpose vision-language models offer a promising way to zero-shot robot control: gptastra{} excels at open-ended and language- or image-condit
arXiv:2609.34384v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have shown strong capabilities in robotic manipulation, yet existing benchmarks typically assume that task-relevan
arXiv:2609.32775v1 Announce Type: new Abstract: Bayesian optimization (BO) is a widely used framework for optimizing expensive black-box objectives, but standard BO methods often use Gaussian process
arXiv:2609.34264v1 Announce Type: new Abstract: We propose a novel optimizer for low-rank adaptation (LoRA) that explicitly incorporates the gauge symmetry of low-rank factorization. Our optimizer ext
arXiv:2609.31918v1 Announce Type: new Abstract: We introduce ROTE (RollOut Testing of Exact memorization), a benchmarking protocol for evaluating symbolic memorization of neural architectures. We stud
arXiv:2609.32821v1 Announce Type: cross Abstract: Model merging efficiently combines specialized large language models (LLMs) without joint retraining, but can substantially alter expert routing in Mi
arXiv:2609.33640v1 Announce Type: new Abstract: Molecular multimodal models support diverse understanding and generation tasks but may introduce safety vulnerabilities when handling hazardous molecule
arXiv:2609.32755v1 Announce Type: cross Abstract: Audio autoencoders compress waveforms into compact latent representations that serve as the interface between raw audio and downstream models. Current
arXiv:2609.34525v1 Announce Type: new Abstract: Diffusion Transformers with Mixture-of-Experts (MoE) routing are a leading recipe for scaling generative models. Classifier-Free Guidance (CFG) is essen
arXiv:2609.34268v1 Announce Type: new Abstract: Large language models (LLMs) are now the default cognitive core of embodied household agents, yet the plans they emit are rarely checked against a groun
arXiv:2609.32108v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models leverage large-scale pretraining to ultimately achieve generalist manipulation. Deployed VLA policies must support c
arXiv:2609.31796v1 Announce Type: new Abstract: Activation probes are increasingly used to monitor LLMs in deployment. A probe is typically trained under one inference configuration, then used under w
arXiv:2609.35333v1 Announce Type: new Abstract: Algorithm Distillation (AD) has demonstrated the remarkable ability of Transformers to perform in-context reinforcement learning without explicit weight
arXiv:2609.32722v1 Announce Type: new Abstract: *Reinforcement learning (RL)* can induce substantial reasoning capabilities in large language models (LLMs), but how much of this capability transfers a
arXiv:2609.34271v1 Announce Type: new Abstract: Although recent 3D generative models produce increasingly realistic assets, controllable 3D asset editing remains challenging. Existing methods are limi
arXiv:2609.33436v1 Announce Type: new Abstract: Attention provides direct access to past representations, but retaining an ever-growing history is costly. Recurrent models bound persistent state, yet
arXiv:2609.33399v1 Announce Type: new Abstract: In realistic education, a solution is often expressed not only in words but in a drawing--a circuit, a geometric construction, a function plot--and a te
arXiv:2609.32391v1 Announce Type: cross Abstract: Continual-learning agents are systems of models, harnesses, and memory operating over long multi-session horizons. Evaluating and training them requir
arXiv:2609.32036v1 Announce Type: new Abstract: We introduce ScreenHaystack, a dynamic needle-in-a-haystack benchmark for evaluating spatial reliability in GUI grounding. Instead of testing each targe
arXiv:2511.15565v3 Announce Type: replace Abstract: Human pose forecasting predicts future human poses from past observations for applications including action recognition, sports analysis, and human-
arXiv:2609.34970v1 Announce Type: new Abstract: Safety-aligned LLMs can exhibit emergent misalignment (EM): narrow domain adaptation unexpectedly triggers catastrophic safety failures across unrelated
arXiv:2609.34277v1 Announce Type: new Abstract: Pathological assessment relies on recognizing fine-grained visual details in histological images. Vision-language models (VLMs) increasingly support pat
arXiv:2603.02772v2 Announce Type: replace Abstract: Motion planners tuned under nominal conditions can fail when execution conditions change. Existing differentiable adaptation methods provide efficie
arXiv:2609.32689v1 Announce Type: new Abstract: LLM-based agents are increasingly used for time-series forecasting because they can organise contextual information, perform multi-step analysis, and gu
arXiv:2609.35576v1 Announce Type: cross Abstract: Large language models are increasingly deployed as stateful assistants that retain information across interactions and use tools to read, modify, and
arXiv:2609.32546v1 Announce Type: new Abstract: Large language models can generate several records within one autoregressive completion, making earlier answers available as context for later records.
Not an LLM, but the ternary findings should carry over, and we hadn't seen Sherry-style 3:4 weights run in a browser before. Disclosure: this is our work at Precisit, everything is MIT. What it is A 7
arXiv:2609.33605v1 Announce Type: new Abstract: Integrated sensing and communication (ISAC) enables joint communication and sensing using a shared waveform, but its signal design is challenging due to
Wanted to try Opus 5.5 because as a plus sub with OAI, Luna just couldn't deliver. Opus is a true beast. It does consume tokens on a medium level yes, but the way it works is just refreshing. But... o
arXiv:2609.32691v1 Announce Type: cross Abstract: LLM agents that invoke privileged tools are vulnerable to indirect prompt injection (IPI), in which adversarial instructions embedded in retrieved dat
arXiv:2609.35295v1 Announce Type: cross Abstract: We address Task A of the 1st DAFx Parameter Estimation Challenge, which aims to retrieve the physical parameters of a plate model from an impulse resp
arXiv:2609.34995v1 Announce Type: cross Abstract: Models of quantum systems faithfully map system parameters to observations, but the inverse problem of parameter inference from measurement data prese
arXiv:2609.34043v1 Announce Type: cross Abstract: Non-negative matrix factorization (NMF) is a singular statistical model whose Bayesian asymptotics are governed by the real log canonical threshold (R
arXiv:2609.32231v1 Announce Type: new Abstract: Human motion prediction requires diverse future trajectories that remain consistent with observed motion and the articulated physical structure of the b
arXiv:2609.33051v1 Announce Type: new Abstract: Hybrid-attention models replace most softmax attention layers with linear attention, reducing KV-cache growth and enabling larger decode batches where r
arXiv:2609.34335v1 Announce Type: new Abstract: Achieving high-quality, cinematic results in text-to-video generation remains challenging for non-experts, whose prompts often lack professional narrati
arXiv:2609.34228v1 Announce Type: new Abstract: Evaluating statistical discovery by large language model (LLM) agents requires verifiable analytical ground truth. Establishing such ground truth for re
arXiv:2609.34117v1 Announce Type: new Abstract: Mixture-of-experts (MoE) models activate few experts per token, yet batched decoding can access nearly the entire expert pool, making expert-weight traf
arXiv:2609.33437v1 Announce Type: new Abstract: Model merging integrates the capabilities of multiple experts without joint retraining, but standard expert training optimizes task loss alone and does
arXiv:2609.33205v1 Announce Type: new Abstract: High-fidelity simulations of time-dependent partial differential equations (PDEs) are computationally expensive, motivating data-driven reduced-order su
arXiv:2609.34681v1 Announce Type: new Abstract: Learning-rate (LR) scheduling plays a central role in large language model (LLM) pretraining, yet current practice still relies heavily on hand-crafted
arXiv:2609.35440v1 Announce Type: new Abstract: Large language models are trained with backpropagation, whose global gradient coordinates all layers but forces each to hold its activations and wait fo
arXiv:2609.35504v1 Announce Type: new Abstract: Machine intelligence is often evaluated through abstract reasoning problems, yet many real-world problems are visual, such as arranging objects, repairi
arXiv:2607.10206v2 Announce Type: replace Abstract: Flow-matching policies are promising for imitation learning because they model complex multimodal action distributions. However, their stochasticity
arXiv:2609.34453v1 Announce Type: new Abstract: This study addresses the catastrophic forgetting problem that occurs when sequentially learning successive tasks using Low-Rank Adaptation (LoRA) from a
arXiv:2609.32592v1 Announce Type: new Abstract: Fixed-capacity streaming video memory requires repeated eviction decisions whose effects accumulate over time. Yet existing policies are evaluated prima
arXiv:2609.35249v1 Announce Type: cross Abstract: Pretrained robot manipulation policies such as vision-language-action models (VLAs) or world-action models (WAMs) leave interaction-relevant metric ge
arXiv:2609.32143v1 Announce Type: new Abstract: Pre-training Graph Neural Networks (GNNs) via self-supervised learning has become a dominant paradigm, yet efficiently adapting frozen encoders remains
arXiv:2609.34019v1 Announce Type: new Abstract: In many high-stakes applications, machine learning is dominated by black-box models that require post hoc explanations to justify their predictions. The
arXiv:2609.35501v1 Announce Type: cross Abstract: Recent agentic symbolic regression approaches increasingly rely on large language models to analyze data, select scientific operations, and refine hyp
arXiv:2609.32615v1 Announce Type: new Abstract: Training neural networks directly in a low-rank parameterization is an appealing route to reducing memory, compute, and storage simultaneously during bo