Bootstrapping Code Translation with Weighted Multilanguage Explorationcs.AI updates on arXiv.org arXiv:2601.03512v1 Announce Type: cross
Abstract: Code translation across multiple programming languages is essential yet challenging due to two vital obstacles: scarcity of parallel data paired with executable test oracles, and optimization imbalance when handling diverse language pairs. We propose BootTrans, a bootstrapping method that resolves both obstacles. Its key idea is to leverage the functional invariance and cross-lingual portability of test suites, adapting abundant pivot-language unit tests to serve as universal verification oracles for multilingual RL training. Our method introduces a dual-pool architecture with seed and exploration pools to progressively expand training data via execution-guided experience collection. Furthermore, we design a language-aware weighting mechanism that dynamically prioritizes harder translation directions based on relative performance across sibling languages, mitigating optimization imbalance. Extensive experiments on the HumanEval-X and TransCoder-Test benchmarks demonstrate substantial improvements over baseline LLMs across all translation directions, with ablations validating the effectiveness of both bootstrapping and weighting components.
arXiv:2601.03512v1 Announce Type: cross
Abstract: Code translation across multiple programming languages is essential yet challenging due to two vital obstacles: scarcity of parallel data paired with executable test oracles, and optimization imbalance when handling diverse language pairs. We propose BootTrans, a bootstrapping method that resolves both obstacles. Its key idea is to leverage the functional invariance and cross-lingual portability of test suites, adapting abundant pivot-language unit tests to serve as universal verification oracles for multilingual RL training. Our method introduces a dual-pool architecture with seed and exploration pools to progressively expand training data via execution-guided experience collection. Furthermore, we design a language-aware weighting mechanism that dynamically prioritizes harder translation directions based on relative performance across sibling languages, mitigating optimization imbalance. Extensive experiments on the HumanEval-X and TransCoder-Test benchmarks demonstrate substantial improvements over baseline LLMs across all translation directions, with ablations validating the effectiveness of both bootstrapping and weighting components. Read More
Efficient Sequential Recommendation for Long Term User Interest Via Personalizationcs.AI updates on arXiv.org arXiv:2601.03479v1 Announce Type: cross
Abstract: Recent years have witnessed success of sequential modeling, generative recommender, and large language model for recommendation. Though the scaling law has been validated for sequential models, it showed inefficiency in computational capacity when considering real-world applications like recommendation, due to the non-linear(quadratic) increasing nature of the transformer model. To improve the efficiency of the sequential model, we introduced a novel approach to sequential recommendation that leverages personalization techniques to enhance efficiency and performance. Our method compresses long user interaction histories into learnable tokens, which are then combined with recent interactions to generate recommendations. This approach significantly reduces computational costs while maintaining high recommendation accuracy. Our method could be applied to existing transformer based recommendation models, e.g., HSTU and HLLM. Extensive experiments on multiple sequential models demonstrate its versatility and effectiveness. Source code is available at href{https://github.com/facebookresearch/PerSRec}{https://github.com/facebookresearch/PerSRec}.
arXiv:2601.03479v1 Announce Type: cross
Abstract: Recent years have witnessed success of sequential modeling, generative recommender, and large language model for recommendation. Though the scaling law has been validated for sequential models, it showed inefficiency in computational capacity when considering real-world applications like recommendation, due to the non-linear(quadratic) increasing nature of the transformer model. To improve the efficiency of the sequential model, we introduced a novel approach to sequential recommendation that leverages personalization techniques to enhance efficiency and performance. Our method compresses long user interaction histories into learnable tokens, which are then combined with recent interactions to generate recommendations. This approach significantly reduces computational costs while maintaining high recommendation accuracy. Our method could be applied to existing transformer based recommendation models, e.g., HSTU and HLLM. Extensive experiments on multiple sequential models demonstrate its versatility and effectiveness. Source code is available at href{https://github.com/facebookresearch/PerSRec}{https://github.com/facebookresearch/PerSRec}. Read More
ReStyle-TTS: Relative and Continuous Style Control for Zero-Shot Speech Synthesiscs.AI updates on arXiv.org arXiv:2601.03632v1 Announce Type: cross
Abstract: Zero-shot text-to-speech models can clone a speaker’s timbre from a short reference audio, but they also strongly inherit the speaking style present in the reference. As a result, synthesizing speech with a desired style often requires carefully selecting reference audio, which is impractical when only limited or mismatched references are available. While recent controllable TTS methods attempt to address this issue, they typically rely on absolute style targets and discrete textual prompts, and therefore do not support continuous and reference-relative style control. We propose ReStyle-TTS, a framework that enables continuous and reference-relative style control in zero-shot TTS. Our key insight is that effective style control requires first reducing the model’s implicit dependence on reference style before introducing explicit control mechanisms. To this end, we introduce Decoupled Classifier-Free Guidance (DCFG), which independently controls text and reference guidance, reducing reliance on reference style while preserving text fidelity. On top of this, we apply style-specific LoRAs together with Orthogonal LoRA Fusion to enable continuous and disentangled multi-attribute control, and introduce a Timbre Consistency Optimization module to mitigate timbre drift caused by weakened reference guidance. Experiments show that ReStyle-TTS enables user-friendly, continuous, and relative control over pitch, energy, and multiple emotions while maintaining intelligibility and speaker timbre, and performs robustly in challenging mismatched reference-target style scenarios.
arXiv:2601.03632v1 Announce Type: cross
Abstract: Zero-shot text-to-speech models can clone a speaker’s timbre from a short reference audio, but they also strongly inherit the speaking style present in the reference. As a result, synthesizing speech with a desired style often requires carefully selecting reference audio, which is impractical when only limited or mismatched references are available. While recent controllable TTS methods attempt to address this issue, they typically rely on absolute style targets and discrete textual prompts, and therefore do not support continuous and reference-relative style control. We propose ReStyle-TTS, a framework that enables continuous and reference-relative style control in zero-shot TTS. Our key insight is that effective style control requires first reducing the model’s implicit dependence on reference style before introducing explicit control mechanisms. To this end, we introduce Decoupled Classifier-Free Guidance (DCFG), which independently controls text and reference guidance, reducing reliance on reference style while preserving text fidelity. On top of this, we apply style-specific LoRAs together with Orthogonal LoRA Fusion to enable continuous and disentangled multi-attribute control, and introduce a Timbre Consistency Optimization module to mitigate timbre drift caused by weakened reference guidance. Experiments show that ReStyle-TTS enables user-friendly, continuous, and relative control over pitch, energy, and multiple emotions while maintaining intelligibility and speaker timbre, and performs robustly in challenging mismatched reference-target style scenarios. Read More
Teaching a Neural Network the Mandelbrot SetTowards Data Science And why Fourier features change everything
The post Teaching a Neural Network the Mandelbrot Set appeared first on Towards Data Science.
And why Fourier features change everything
The post Teaching a Neural Network the Mandelbrot Set appeared first on Towards Data Science. Read More
Author: Derrick D. JacksonTitle: Founder & Senior Director of Cloud Security Architecture & RiskCredentials: CISSP, CRISC, CCSPLast updated: January 8th, 2026 Hello Everyone, Help us grow our community by sharing and/or supporting us on other platforms. This allow us to show verification that what we are doing is valued. It also allows us to plan and […]
The North Korean state-sponsored hacker group Kimsuki is using malicious QR codes in spearphishing campaigns that target U.S. organizations, the Federal Bureau of Investigation warns in a flash alert. […] Read More
Netomi’s lessons for scaling agentic systems into the enterpriseOpenAI News How Netomi scales enterprise AI agents using GPT-4.1 and GPT-5.2—combining concurrency, governance, and multi-step reasoning for reliable production workflows.
How Netomi scales enterprise AI agents using GPT-4.1 and GPT-5.2—combining concurrency, governance, and multi-step reasoning for reliable production workflows. Read More
10 Most Popular GitHub Repositories for Learning AIKDnuggets The most popular GitHub repositories to help you learn AI, from fundamentals and math to LLMs, agents, computer vision, and real-world production systems.
The most popular GitHub repositories to help you learn AI, from fundamentals and math to LLMs, agents, computer vision, and real-world production systems. Read More
“Dr AI, am I healthy?” 59% of Brits rely on AI for self-diagnosisAI News AI advancements are changing the way we look at health and deal with health-related issues. According to a new nationwide study by Confused.com Life Insurance, three in five Brits now use AI to self-diagnose health conditions. Through various searches, like side effects of medical conditions, treatment options, and symptom checks, as much as 11% of
The post “Dr AI, am I healthy?” 59% of Brits rely on AI for self-diagnosis appeared first on AI News.
AI advancements are changing the way we look at health and deal with health-related issues. According to a new nationwide study by Confused.com Life Insurance, three in five Brits now use AI to self-diagnose health conditions. Through various searches, like side effects of medical conditions, treatment options, and symptom checks, as much as 11% of
The post “Dr AI, am I healthy?” 59% of Brits rely on AI for self-diagnosis appeared first on AI News. Read More
How to Improve the Performance of Visual Anomaly Detection ModelsTowards Data Science Apply the best methods from academia to get the most out of practical applications
The post How to Improve the Performance of Visual Anomaly Detection Models appeared first on Towards Data Science.
Apply the best methods from academia to get the most out of practical applications
The post How to Improve the Performance of Visual Anomaly Detection Models appeared first on Towards Data Science. Read More
