Everyday speech conveys far more than words, it reflects who we are, how we feel, and the circumstances surrounding our interactions. Yet, most existing speech datasets are acted, limited in scale, and fail to capture the expressive richness of real-life communication. With the rise of large neural networks, several large-scale speech corpora have emerged and been widely adopted across various speech processing tasks. However, the field of voice conversion (VC) still lacks large-scale, expressive, and real-life speech resources suitable for modeling natural prosody and emotion. To fill this gap, we release NaturalVoices (NV), the first large-scale spontaneous podcast dataset specifically designed for emotion-aware voice conversion. It comprises 5,049 hours of spontaneous podcast recordings with automatic annotations for emotion (categorical and attribute-based), speech quality, transcripts, speaker identity, and sound events. The dataset captures expressive emotional variation across thousands of speakers, diverse topics, and natural speaking styles. We also provide an open-source pipeline with modular annotation tools and flexible filtering, enabling researchers to construct customized subsets for a wide range of VC tasks. Experiments demonstrate that NaturalVoices supports the development of robust and generalizable VC models capable of producing natural, expressive speech, while revealing limitations of current architectures when applied to large-scale spontaneous data. These results suggest that NaturalVoices is both a valuable resource and a challenging benchmark for advancing the field of voice conversion. Dataset is available at: https://huggingface.co/JHU-SmileLab

Optimizing training performance in large language models (LLMs) remains an essential challenge, particularly in improving model performance while maintaining computational costs. This work challenges the conventional approach of training LLMs using next-token prediction (NTP), arguing that by predicting information-rich tokens during training, there is a more effective way to train LLMs. We investigate the impact of the proposed solution in three kinds of tasks for LLMs: arithmetic, multi-label classification of text, and natural-language generation. This work offers a principled approach to optimizing LLM training, advancing both model performance and theoretical understanding of the target-token selection strategies.

Large Language Model (LLM) agents have recently shown strong potential in domains such as automated coding, deep research, and graphical user interface manipulation. However, training them to succeed on long-horizon, domain-specialized tasks remains challenging. Current methods primarily fall into two categories. The first relies on dense human annotations through behavior cloning, which is prohibitively expensive for long-horizon tasks that can take days or months. The second depends on outcome-driven sampling, which often collapses due to the rarity of valid positive trajectories on domain-specialized tasks. We introduce Apollo, a sampling framework that integrates asynchronous human guidance with action-level data filtering. Instead of requiring annotators to shadow every step, Apollo allows them to intervene only when the agent drifts from a promising trajectory, by providing prior knowledge, strategic advice, etc. This lightweight design makes it possible to sustain interactions for over 30 hours and produces valuable trajectories at a lower cost. Apollo then applies supervision control to filter out sub-optimal actions and prevent error propagation. Together, these components enable reliable and effective data collection in long-horizon environments. To demonstrate the effectiveness of Apollo, we evaluate it using InnovatorBench. Our experiments show that when applied to train the GLM-4.5 model on InnovatorBench, Apollo achieves more than a 50% improvement over the untrained baseline and a 28% improvement over a variant trained without human interaction. These results highlight the critical role of human-in-the-loop sampling and the robustness of Apollo's design in handling long-horizon, domain-specialized tasks.

AI agents could accelerate scientific discovery by automating hypothesis formation, experiment design, coding, execution, and analysis, yet existing benchmarks probe narrow skills in simplified settings. To address this gap, we introduce InnovatorBench, a benchmark-platform pair for realistic, end-to-end assessment of agents performing Large Language Model (LLM) research. It comprises 20 tasks spanning Data Construction, Filtering, Augmentation, Loss Design, Reward Design, and Scaffold Construction, which require runnable artifacts and assessment of correctness, performance, output quality, and uncertainty. To support agent operation, we develop ResearchGym, a research environment offering rich action spaces, distributed and long-horizon execution, asynchronous monitoring, and snapshot saving. We also implement a lightweight ReAct agent that couples explicit reasoning with executable planning using frontier models such as Claude-4, GPT-5, GLM-4.5, and Kimi-K2. Our experiments demonstrate that while frontier models show promise in code-driven research tasks, they struggle with fragile algorithm-related tasks and long-horizon decision making, such as impatience, poor resource management, and overreliance on template-based reasoning. Furthermore, agents require over 11 hours to achieve their best performance on InnovatorBench, underscoring the benchmark's difficulty and showing the potential of InnovatorBench to be the next generation of code-based research benchmark.

Efficient large-scale retrieval requires representations that are both compact and discriminative. Foundation models provide powerful visual and multimodal embeddings, but nearest neighbor search in these high-dimensional spaces is computationally expensive. Hashing offers an efficient alternative by enabling fast Hamming distance search with binary codes, yet existing approaches often rely on complex pipelines, multi-term objectives, designs specialized for a single learning paradigm, and long training times. We introduce CroVCA (Cross-View Code Alignment), a simple and unified principle for learning binary codes that remain consistent across semantically aligned views. A single binary cross-entropy loss enforces alignment, while coding-rate maximization serves as an anti-collapse regularizer to promote balanced and diverse codes. To implement this, we design HashCoder, a lightweight MLP hashing network with a final batch normalization layer to enforce balanced codes. HashCoder can be used as a probing head on frozen embeddings or to adapt encoders efficiently via LoRA fine-tuning. Across benchmarks, CroVCA achieves state-of-the-art results in just 5 training epochs. At 16 bits, it particularly well-for instance, unsupervised hashing on COCO completes in under 2 minutes and supervised hashing on ImageNet100 in about 3 minutes on a single GPU. These results highlight CroVCA's efficiency, adaptability, and broad applicability.

We introduce Kimi Linear, a hybrid linear attention architecture that, for the first time, outperforms full attention under fair comparisons across various scenarios -- including short-context, long-context, and reinforcement learning (RL) scaling regimes. At its core lies Kimi Delta Attention (KDA), an expressive linear attention module that extends Gated DeltaNet with a finer-grained gating mechanism, enabling more effective use of limited finite-state RNN memory. Our bespoke chunkwise algorithm achieves high hardware efficiency through a specialized variant of the Diagonal-Plus-Low-Rank (DPLR) transition matrices, which substantially reduces computation compared to the general DPLR formulation while remaining more consistent with the classical delta rule. We pretrain a Kimi Linear model with 3B activated parameters and 48B total parameters, based on a layerwise hybrid of KDA and Multi-Head Latent Attention (MLA). Our experiments show that with an identical training recipe, Kimi Linear outperforms full MLA with a sizeable margin across all evaluated tasks, while reducing KV cache usage by up to 75% and achieving up to 6 times decoding throughput for a 1M context. These results demonstrate that Kimi Linear can be a drop-in replacement for full attention architectures with superior performance and efficiency, including tasks with longer input and output lengths. To support further research, we open-source the KDA kernel and vLLM implementations, and release the pre-trained and instruction-tuned model checkpoints.

Multi-page visual documents such as manuals, brochures, presentations, and posters convey key information through layout, colors, icons, and cross-slide references. While large language models (LLMs) offer opportunities in document understanding, current systems struggle with complex, multi-page visual documents, particularly in fine-grained reasoning over elements and pages. We introduce SlideAgent, a versatile agentic framework for understanding multi-modal, multi-page, and multi-layout documents, especially slide decks. SlideAgent employs specialized agents and decomposes reasoning into three specialized levels-global, page, and element-to construct a structured, query-agnostic representation that captures both overarching themes and detailed visual or textual cues. During inference, SlideAgent selectively activates specialized agents for multi-level reasoning and integrates their outputs into coherent, context-aware answers. Extensive experiments show that SlideAgent achieves significant improvement over both proprietary (+7.9 overall) and open-source models (+9.8 overall).

Diacritics restoration in Hebrew is a fundamental task for ensuring accurate word pronunciation and disambiguating textual meaning. Despite the language's high degree of ambiguity when unvocalized, recent machine learning approaches have significantly advanced performance on this task. In this work, we present DIVRIT, a novel system for Hebrew diacritization that frames the task as a zero-shot classification problem. Our approach operates at the word level, selecting the most appropriate diacritization pattern for each undiacritized word from a dynamically generated candidate set, conditioned on the surrounding textual context. A key innovation of DIVRIT is its use of a Hebrew Visual Language Model, which processes undiacritized text as an image, allowing diacritic information to be embedded directly within the input's vector representation. Through a comprehensive evaluation across various configurations, we demonstrate that the system effectively performs diacritization without relying on complex, explicit linguistic analysis. Notably, in an ``oracle'' setting where the correct diacritized form is guaranteed to be among the provided candidates, DIVRIT achieves a high level of accuracy. Furthermore, strategic architectural enhancements and optimized training methodologies yield significant improvements in the system's overall generalization capabilities. These findings highlight the promising potential of visual representations for accurate and automated Hebrew diacritization.

Large language models (LLMs) have increasingly been applied to automatic programming code generation. This task can be viewed as a language generation task that bridges natural language, human knowledge, and programming logic. However, it remains underexplored in domains that require interaction with hardware devices, such as quantum programming, where human coders write Python code that is executed on a quantum computer. To address this gap, we introduce QCoder Benchmark, an evaluation framework that assesses LLMs on quantum programming with feedback from simulated hardware devices. Our benchmark offers two key features. First, it supports evaluation using a quantum simulator environment beyond conventional Python execution, allowing feedback of domain-specific metrics such as circuit depth, execution time, and error classification, which can be used to guide better generation. Second, it incorporates human-written code submissions collected from real programming contests, enabling both quantitative comparisons and qualitative analyses of LLM outputs against human-written codes. Our experiments reveal that even advanced models like GPT-4o achieve only around 18.97% accuracy, highlighting the difficulty of the benchmark. In contrast, reasoning-based models such as o3 reach up to 78% accuracy, outperforming averaged success rates of human-written codes (39.98%). We release the QCoder Benchmark dataset and public evaluation API to support further research. (Codes and datasets are available at https://qcoder-bench.github.io/ )

In control problems and basic scientific modeling, it is important to compare observations with dynamical simulations. For example, comparing two neural systems can shed light on the nature of emergent computations in the brain and deep neural networks. Recently, Ostrow et al. (2023) introduced Dynamical Similarity Analysis (DSA), a method to measure the similarity of two systems based on their recurrent dynamics rather than geometry or topology. However, DSA does not consider how inputs affect the dynamics, meaning that two similar systems, if driven differently, may be classified as different. Because real-world dynamical systems are rarely autonomous, it is important to account for the effects of input drive. To this end, we introduce a novel metric for comparing both intrinsic (recurrent) and input-driven dynamics, called InputDSA (iDSA). InputDSA extends the DSA framework by estimating and comparing both input and intrinsic dynamic operators using a variant of Dynamic Mode Decomposition with control (DMDc) based on subspace identification. We demonstrate that InputDSA can successfully compare partially observed, input-driven systems from noisy data. We show that when the true inputs are unknown, surrogate inputs can be substituted without a major deterioration in similarity estimates. We apply InputDSA on Recurrent Neural Networks (RNNs) trained with Deep Reinforcement Learning, identifying that high-performing networks are dynamically similar to one another, while low-performing networks are more diverse. Lastly, we apply InputDSA to neural data recorded from rats performing a cognitive task, demonstrating that it identifies a transition from input-driven evidence accumulation to intrinsically-driven decision-making. Our work demonstrates that InputDSA is a robust and efficient method for comparing intrinsic dynamics and the effect of external input on dynamical systems.