Recent progress in Sign Language Translation (SLT) has focussed primarily on improving the representational capacity of large language models to incorporate Sign Language features. This work explores an alternative direction: enhancing the geometric properties of skeletal representations themselves. We propose GeoSign, a method that leverages the properties of hyperbolic geometry to model the hierarchical structure inherent in sign language kinematics. By projecting skeletal features derived from Spatio-Temporal Graph Convolutional Networks (ST-GCNs) into the Poincaré ball model, we aim to create more discriminative embeddings, particularly for fine-grained motions like finger articulations. We introduce a hyperbolic projection layer, a weighted Fréchet mean aggregation scheme, and a geometric contrastive loss operating directly in hyperbolic space. These components are integrated into an end-to-end translation framework as a regularisation function, to enhance the representations within the language model. This work demonstrates the potential of hyperbolic geometry to improve skeletal representations for Sign Language Translation, improving on SOTARGB methods while preserving privacy and improving computational efficiency.

Foundation Vision Encoders have become essential for a wide range of dense vision tasks. However, their low-resolution spatial feature outputs necessitate feature upsampling to produce the high-resolution modalities required for downstream tasks. In this work, we introduce JAFAR, a lightweight and flexible feature upsampler that enhances the spatial resolution of visual features from any Foundation Vision Encoder to an arbitrary target resolution. JAFAR employs an attention-based module designed to promote semantic alignment between high-resolution queries, derived from low-level image features, and semantically enriched low-resolution keys, using Spatial Feature Transform (SFT) modulation. Notably, despite the absence of high-resolution supervision, we demonstrate that learning at low upsampling ratios and resolutions generalizes remarkably well to significantly higher output scales. Extensive experiments show that JAFAR effectively recovers fine-grained spatial details and consistently outperforms existing feature upsampling methods across a diverse set of downstream tasks.

As multimodal large models (MLLMs) continue to advance across challenging tasks, a key question emerges: What essential capabilities are still missing? A critical aspect of human learning is continuous interaction with the environment - not limited to language, but also involving multimodal understanding and generation. To move closer to human-level intelligence, models must similarly support multi-turn, multimodal interaction. In particular, they should comprehend interleaved multimodal contexts and respond coherently in ongoing exchanges. In this work, we present an initial exploration through the INTERMT - the first preference dataset for multi-turn multimodal interaction, grounded in real human feedback.

This follows a smartphone and tablet ban in classrooms. Norway is imposing a strict ban on the use of generative AI tools by elementary school kids, according to a report by . Prime Minister Jonas Gahr Stoere suggested at a press conference that AI lets children skip crucial steps in their education and that schools should focus on teaching them how to read, write and do mathematics. These standards will be imposed at the start of the new school year, which begins in late August. However, the policy also extends to teens, albeit in a reduced fashion.

The increase in computing power and the necessity of AI-assisted decision-making boost the growing application of Large Language Models (LLMs). Along with this, the potential retention of sensitive data of LLMs has spurred increasing research into machine unlearning. However, existing unlearning approaches face a critical dilemma: Aggressive unlearning compromises model utility, while conservative strategies preserve utility but risk hallucinated responses. This significantly limits LLMs' reliability in knowledge-intensive applications. To address this, we introduce a novel Attention-Shifting (AS) framework for selective unlearning.

One of only four teams remaining from more than 130 competitors worldwide, our team AURA Foresight is developing autonomous technology to stop wildfires before they grow out of control. AURA Foresight has been selected as a finalist in the prestigious XPRIZE Wildfire Autonomous Wildfire Response competition, emerging as one of just four teams remaining from more than 130 teams from around the world. XPRIZE Wildfire is a four-year, US$11 million global competition designed to accelerate breakthrough technologies capable of ending destructive wildfires. The Autonomous Wildfire Response track, worth US$5 million, challenges teams to autonomously detect, verify and respond to wildfire ignitions across a 1,000 km landscape within just ten minutes. The finals will take place in Nenana, Alaska, where teams will demonstrate their technologies in realistic wildfire response scenarios.

Algorithms for learning decision trees often include heuristic local-search operations such as (1) adjusting the threshold of a cut or (2) also exchanging the feature of that cut. We study minimizing the number of classification errors by performing a fixed number of a single type of these operations. Although we discover that the corresponding problems are NP-complete in general, we provide a comprehensive parameterized-complexity analysis with the aim of determining those properties of the problems that explain the hardness and those that make the problems tractable. For instance, we show that the problems remain hard for a small number d of features or small domain size D but the combination of both yields fixed-parameter tractability. That is, the problems are solvable in (D+1)2d |I|O(1) time, where |I|is the size of the input. We also provide a proof-of-concept implementation of this algorithm and report on empirical results.

Multi-compartment Hodgkin-Huxley models are biophysical models of how electrical signals propagate throughout a neuron, and they form the basis of our knowledge of neural computation at the cellular level. However, these models have many free parameters that must be estimated for each cell, and existing fitting methods rely on intracellular voltage measurements that are highly challenging to obtain in vivo. Recent advances in neural recording technology with high-density probes and arrays enable dense sampling of extracellular voltage from many sites surrounding a neuron, allowing indirect measurement of many compartments of a cell simultaneously. Here, we propose a method for inferring the underlying membrane voltage, biophysical parameters, and the neuron's position relative to the probe, using extracellular measurements alone. We use an Extended Kalman Filter to infer membrane voltage and channel states using efficient, differentiable simulators. Then, we learn the model parameters by maximizing the marginal likelihood using gradient-based methods. We demonstrate the performance of this approach using simulated data and real neuron morphologies.

Visual processing starts in the outer retina where photoreceptors transform light into electrochemical signals. These signals are modulated by inhibition from horizontal cells and sent to the inner retina via excitatory bipolar cells. The outer retina is thought to play an important role in contrast invariant coding of visual information, but how the different cell types implement this computation together remains incompletely understood. To understand the role of each cell type, we developed a fully-differentiable biophysical model of a circular patch of mouse outer retina. The model includes 200 cone photoreceptors with a realistic phototransduction cascade and ribbon synapses as well as horizontal and bipolar cells, all with celltype specific ion channels. Going beyond decades of work constraining biophysical models of neurons only by experimental data, we used a dual approach, constraining some parameters of the model with available measurements and others by a visual task: (1) We fit the parameters of the cone models to whole cell patch-clamp measurements of photocurrents and two-photon glutamate imaging measurements of synaptic release.

We introduce IndEgo, a multimodal egocentric and exocentric dataset addressing common industrial tasks, including assembly/disassembly, logistics and organisation, inspection and repair, woodworking, and others. The dataset contains 3,460 egocentric recordings (approximately 197 hours), along with 1,092 exocentric recordings (approximately 97 hours). A key focus of the dataset is collaborative work, where two workers jointly perform cognitively and physically intensive tasks. The egocentric recordings include rich multimodal data and added context via eye gaze, narration, sound, motion, and others. We provide detailed annotations (actions, summaries, mistake annotations, narrations), metadata, processed outputs (eye gaze, hand pose, semi-dense point cloud), and benchmarks on procedural and non-procedural task understanding, Mistake Detection, and reasoning-based Question Answering.