Fine-grained visual classification (FGVC) requires distinguishing between visually similar categories through subtle, localized features - a task that remains challenging due to high intra-class variability and limited inter-class differences. Existing part-based methods often rely on complex localization networks that learn mappings from pixel to sample space, requiring a deep understanding of image content while limiting feature utility for downstream tasks. In addition, sampled points frequently suffer from high spatial redundancy, making it difficult to quantify the optimal number of required parts. Inspired by human saccadic vision, we propose a two-stage process that first extracts peripheral features (coarse view) and generates a sample map, from which fixation patches are sampled and encoded in parallel using a weight-shared encoder. We employ contextualized selective attention to weigh the impact of each fixation patch before fusing peripheral and focus representations. To prevent spatial collapse - a common issue in part-based methods - we utilize non-maximum suppression during fixation sampling to eliminate redundancy. Comprehensive evaluation on standard FGVC benchmarks (CUB-200-2011, NABirds, Food-101 and Stanford-Dogs) and challenging insect datasets (EU-Moths, Ecuador-Moths and AMI-Moths) demonstrates that our method achieves comparable performance to state-of-the-art approaches while consistently outperforming our baseline encoder.

Standard Behavior Cloning (BC) fails to learn multimodal driving decisions, where multiple valid actions exist for the same scenario. W e explore Implicit Behavioral Cloning (IBC) with Energy-Based Models (EBMs) to better capture this multimodality. W e propose Data-Augmented IBC (DA-IBC), which improves learning by perturbing expert actions to form the counterexamples of IBC training and using better initialization for derivative-free inference. Experiments in the CARLA simulator with Bird's-Eye View inputs demonstrate that DA-IBC outperforms standard IBC in urban driving tasks designed to evaluate multimodal behavior learning in a test environment. The learned energy landscapes are able to represent multimodal action distributions, which BC fails to achieve.

Recent work has investigated the capabilities of large language models (LLMs) as zero-shot models for generating individual-level characteristics (e.g., to serve as risk models or augment survey datasets). However, when should a user have confidence that an LLM will provide high-quality predictions for their particular task? To address this question, we conduct a large-scale empirical study of LLMs' zero-shot predictive capabilities across a wide range of tabular prediction tasks. We find that LLMs' performance is highly variable, both on tasks within the same dataset and across different datasets. However, when the LLM performs well on the base prediction task, its predicted probabilities become a stronger signal for individual-level accuracy. Then, we construct metrics to predict LLMs' performance at the task level, aiming to distinguish between tasks where LLMs may perform well and where they are likely unsuitable. We find that some of these metrics, each of which are assessed without labeled data, yield strong signals of LLMs' predictive performance on new tasks.

Why is Israel still in southern Lebanon? A war to shape Lebanon's future An Israeli drone strike has killed five people, including three children, in the southern Lebanese town of Bint Jbeil, Lebanon's Health Ministry has said, as Israel continues to target its neighbour despite a US-brokered truce that took effect in November. The state-run National News Agency (NNA) reported on Sunday that the strike targeted a motorcycle and a vehicle, and wounded two other people. Why then did Israel attack Syria? The mother of the children was injured in the attack.

WIRED went to Brazil for YouTube's first live NFL broadcast. It was helmed by the platform's biggest influencers as the league expands its quest for global domination. Kay Adams, Deestroying, haleyybaylee, and Cam Newton at YouTube's first live NFL broadcast. The first international game of the National Football League season, a Friday-night tilt between the Kansas City Chiefs and Los Angeles Chargers in São Paulo, is celebrated on the ground by the usual pomp and circumstance. There are photo booths and merch tents catering to local fans, samba dancers in feathered head-pieces entertaining American die-hards traveling across the equator, and a press conference where Chiefs quarterback Patrick Mahomes has to backtrack after calling association football (that is, the kind that is still most popular in Brazil, and the rest of the word) "soccer."

A secret Russian-funded network is attempting to disrupt upcoming democratic elections in an eastern European state, the BBC has found. Using an undercover reporter, we discovered the network promised to pay participants if they posted pro-Russian propaganda and fake news undermining Moldova's pro-EU ruling party ahead of the country's 28 September parliamentary ballot. Participants were paid to find supporters of Moldova's pro-Russia opposition to secretly record - and also to carry out a so-called poll. This was done in the name of a non-existent organisation, making it illegal. The results of this selective sampling, an organiser from the network suggested, could lay the groundwork to question the outcome of the election.

UN'gravely alarmed' by deteriorating situation in Sudan's el-Fasher The United Nations secretary-general has called for an immediate ceasefire in Sudan's Darfur region after a deadly drone attack on Friday killed more than 70 worshippers in el-Fasher, expressing "grave" alarm about the "rapidly deteriorating situation". "The fighting must stop now," Antonio Guterres said in a statement issued by his spokesperson on Saturday, urging the warring parties to engage in dialogue and provide humanitarian corridors, with the brutal civil war wracking the nation in its third year. El-Fasher, the capital of the North Darfur region, remains the government-backed Sudanese Armed Forces (SAF) and its allies' last major stronghold across Darfur. It has been under siege for more than a year by the paramilitary Rapid Support Forces (RSF), which launched a renewed offensive to capture the city in recent weeks. Humanitarian organisations have raised alarm about growing hunger in the city as hundreds of thousands of people remain trapped without access to food, medicine and other essentials.

History in the making as Rwanda hosts the 2025 UCI Road World Championships - the first time cycling's crown jewel comes to Africa. Al Jazeera's Samantha Johnson asks if this moment can change the sport and the continent forever?

How is Russia replenishing its military? What is a'coalition of the willing'? How China forgot promises and'debts' to Ukraine How are Europe, the US pulling apart on Ukraine? Russian forces launched a large-scale missile and drone attack, targeting areas across Ukraine, killing at least three people and wounding dozens more, according to Ukrainian officials. Ukrainian President Volodymyr Zelenskyy said Russia launched 580 drones and 40 missiles, and that the attacks took place across nine regions, including Dnipropetrovsk, Mykolaiv, Chernihiv, Zaporizhia, Poltava, Kyiv, Odesa, Sumy and Kharkiv.

Dating apps, booze and clubbing - Jane Austen's Emma comes into the 21st Century And your pushy best friend is trying to sort out your love life. It's Jane Austen's Emma, but not as you know it. For the uninitiated, the 1815 novel follows the charmed life of our protagonist in Regency England as she busies herself interfering in her friends' relationships (or matchmaking, depending on your point of view). In Ava Pickett's fresh adaptation, being staged at London's Rose Theatre, Emma Woodhouse still has all the trademark traits of our beloved original heroine - she's clever, quick-witted, meddling, haughty and occasionally cruel. But instead of navigating society balls and dowries, Pickett's modern Emma is poking her nose into her friends' online dating profiles, having returned home after failing her exams at Oxford University.