Speech emotion recognition (SER) systems often exhibit gender bias. However, the effectiveness and robustness of existing debiasing methods in such multi-label scenarios remain underexplored. To address this gap, we present EMO-Debias, a large-scale comparison of 13 debiasing methods applied to multi-label SER. Our study encompasses techniques from pre-processing, regularization, adversarial learning, biased learners, and distributionally robust optimization. Experiments conducted on acted and naturalistic emotion datasets, using WavLM and XLSR representations, evaluate each method under conditions of gender imbalance. Our analysis quantifies the trade-offs between fairness and accuracy, identifying which approaches consistently reduce gender performance gaps without compromising overall model performance. The findings provide actionable insights for selecting effective debiasing strategies and highlight the impact of dataset distributions.

Network Intrusion Detection Systems (NIDS) play a vital role in protecting digital infrastructures against increasingly sophisticated cyber threats. In this paper, we extend ODXU, a Neurosymbolic AI (NSAI) framework that integrates deep embedded clustering for feature extraction, symbolic reasoning using XGBoost, and comprehensive uncertainty quantification (UQ) to enhance robustness, interpretability, and generalization in NIDS. The extended ODXU incorporates score-based methods (e.g., Confidence Scoring, Shannon Entropy) and metamodel-based techniques, including SHAP values and Information Gain, to assess the reliability of predictions. Experimental results on the CIC-IDS-2017 dataset show that ODXU outperforms traditional neural models across six evaluation metrics, including classification accuracy and false omission rate. While transfer learning has seen widespread adoption in fields such as computer vision and natural language processing, its potential in cybersecurity has not been thoroughly explored. To bridge this gap, we develop a transfer learning strategy that enables the reuse of a pre-trained ODXU model on a different dataset. Our ablation study on ACI-IoT-2023 demonstrates that the optimal transfer configuration involves reusing the pre-trained autoencoder, retraining the clustering module, and fine-tuning the XGBoost classifier, and outperforms traditional neural models when trained with as few as 16,000 samples (approximately 50% of the training data). Additionally, results show that metamodel-based UQ methods consistently outperform score-based approaches on both datasets.

A fundamental problem in organic chemistry is identifying and predicting the series of reactions that synthesize a desired target product molecule. Due to the combinatorial nature of the chemical search space, single-step reactant prediction -- i.e. single-step retrosynthesis -- remains challenging even for existing state-of-the-art template-free generative approaches to produce an accurate yet diverse set of feasible reactions. In this paper, we model single-step retrosynthesis planning and introduce RETRO SYNFLOW (RSF) a discrete flow-matching framework that builds a Markov bridge between the prescribed target product molecule and the reactant molecule. In contrast to past approaches, RSF employs a reaction center identification step to produce intermediate structures known as synthons as a more informative source distribution for the discrete flow. To further enhance diversity and feasibility of generated samples, we employ Feynman-Kac steering with Sequential Monte Carlo based resampling to steer promising generations at inference using a new reward oracle that relies on a forward-synthesis model. Empirically, we demonstrate \nameshort achieves $60.0 \%$ top-1 accuracy, which outperforms the previous SOTA by $20 \%$. We also substantiate the benefits of steering at inference and demonstrate that FK-steering improves top-$5$ round-trip accuracy by $19 \%$ over prior template-free SOTA methods, all while preserving competitive top-$k$ accuracy results.

--This paper proposes FLUC, a modular framework that integrates open-source Large Language Models (LLMs) with Unmanned Aerial V ehicle (UA V) autopilot systems to enable autonomous control in Flying Networks (FNs). FLUC is evaluated using three open-source LLMs - Qwen 2.5, Gemma 2, and LLaMA 3.2 - across scenarios involving code generation and mission planning. Results show that Qwen 2.5 excels in multi-step reasoning, Gemma 2 balances accuracy and latency, and LLaMA 3.2 offers faster responses with lower logical coherence. A case study on energy-aware UA V positioning confirms FLUC's ability to interpret structured prompts and autonomously execute domain-specific logic, showing its effectiveness in real-time, mission-driven control. The demand for adaptable and reliable wireless communications systems has led to the adoption of Flying Networks (FNs), where Unmanned Aerial V ehicles (UA Vs) act as airborne communications nodes. FNs provide on-demand network coverage in scenarios where terrestrial infrastructure is infeasible or insufficient, such as disaster response, large-scale events, and remote rural areas (see Figure 1).

Elon Musk quickly began pulling the plug on federal projects amid an escalating feud with Donald Trump, but the high-stakes clash now further threatens the most prized asset in his empire. With Tesla shares in freefall and SpaceX contracts on the line, the ambitious megaproject Musk most needs to compete in the AI race could become collateral in the explosive back-and-forth. Built in Tennessee, the supercomputer Colossus powers Musk's artificial intelligence company, xAI. The vast facility cost an estimated 4 billion and Musk plans to spend tens of billions more expanding it in a bid to challenge AI giants OpenAI and Google. However, it is already mired in an explosive backlash that the president could seize on.

It only took a few hours to wipe 152 billion of value from Tesla's market cap and more than 100 million in value from TrumpCoin. The end of the bromance between Elon Musk and President Donald Trump has been brewing for weeks, but on Thursday, the breakup went nuclear. Musk took to the platform he owns, X, to lambast Trump's "One Big Beautiful Bill," which includes provisions that restrict immigration, limit green energy subsidies, and is estimated to increase the US deficit by 2.4 trillion. Trump shot back on Truth Social, the platform he owns, to say that Musk was only against the bill because it would take away electric vehicle tax credits that Musk's company, Tesla, benefits from. It quickly devolved into dozens of posts, most of them from Musk, who claimed Trump is in the Epstein Files--which is, he claims, why they haven't been made public. Tesla's stock is now down roughly 14 percent at the time of writing, which is the biggest single-day hit to its market cap in years.

Weekly quiz: What did Taylor Swift buy back? This week saw Ukraine mount an audacious drone attack on Russian airfields, Donald Trump ban people in 12 countries from travelling to the US, while Billie Piper returned to Doctor Who. But how much attention did you pay to what else happened in the world? Try last week's quiz, or have a go at something from the archives.Taylor SwiftMusicRelated The 43-year-old global superstar performed the first night of her six show residency in London.2 The star says he is focusing on acting after parting ways with his record company.3 hrs agoCulture8 hrs ago The annual event kicks off on Thursday and runs until the end of June.8 hrs ago Northern Ireland13 hrs ago Cally Rhodes from Shrewsbury says being selected to perform with Murs at Ludlow Castle is "unreal".13 Paul Weller cover version'the ultimate tribute' to Friel The family Eamon Friel tell Paul Weller they are delighted with his version of El Dorado.15

Joe Rogan has warned that the end of the world may be only 10 years away and it will come at the hands of humanity's'new God.' In what's being called one of the podcast host's best episode ever on social media, Rogan and guest Jesse Michels discussed the ominous signs that artificial intelligence (AI) has already shown signs of taking over the world. Michels, host of the American Alchemy podcast, warned about AI's deceptive nature, job-replacing power, risk of sentience, and potential to disrupt society if left unchecked. Rogan then highlighted shocking language buried in Congress's'Big Beautiful Bill' which would prohibit lawmakers from regulating the power of AI for the next 10 years. 'That's so crazy,' Rogan declared during the June 3 podcast. 'This means that US states would be blocked from enforcing laws regulating AI and automated decision systems for 10 years.

Russia is vowing Thursday to repair the warplanes damaged by Ukraine in a massive drone attack earlier this week, with an official claiming they were "not destroyed but damaged." The comments from Russian Deputy Foreign Minister Sergey Ryabkov come after Ukraine said its forces destroyed 40 of Russia's most powerful bomber jets and surveillance planes in "Operation Spider's Web," a series of coordinated drone strikes Sunday penetrating deep into Russian territory. "As the defense ministry said, these aircraft were not destroyed but damaged. They will be repaired," Ryabkov was quoted telling Russia's state-run TASS news agency. However, satellite images of Russian airfields show extensive damage to the planes.

Fox News contributor Dan Hoffman joins'Fox & Friends' to discuss the latest on the fallout from Ukraine's bombing of a bridge connecting Russia and Crimea and the push for NATO defense spending. Pope Leo XIV has made a direct plea for peace with Ukraine to Russian President Vladimir Putin in their first call since the American pontiff took up the highest seat in the Catholic Church last month. Following the call on Wednesday, the Vatican said the pope emphasized the "importance of dialogue" though it is unclear if he encouraged Putin to engage in direct discussions with his Ukrainian counterpart, President Volodymyr Zelenskyy, which the Kremlin chief has so far refused to do. While the pair also discussed humanitarian issues, prisoner exchanges and aid, Putin also apparently accused Kyiv of "escalating" the war during the phone call. An explosion is seen Tuesday, June 3, along the Kerch Bridge linking Russia and Crimea.