3,698 items tracked: 33 reported by two or more outlets, the rest by a single source. Most-corroborated first.
arXiv:2610.16466v1 Announce Type: cross Abstract: We present PatMT2 (Patent Machine Translation, v2), a two-stage LoRA pipeline that adapts the Hy-MT2-7B dedicated translation model to four-language (Chinese/English/Japa…
arXiv:2610.16484v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models scale model capacity efficiently by activating only a small subset of experts for each input, while still requiring all parameters to be s…
arXiv:2610.16489v1 Announce Type: cross Abstract: Reinforcement learning (RL) can substantially improve the reasoning capabilities of large language models, but an effective training run requires considerable resources.
arXiv:2610.16498v1 Announce Type: cross Abstract: Generative Social Simulation (GSS) leverages Large Language Models (LLMs) to create sophisticated personas that define agents with demographics, emotions, and political o…
arXiv:2610.16504v1 Announce Type: cross Abstract: Developing reliable predictive models for multi-physics systems often forces a compromise between computationally demanding physical simulators and data-hungry, opaque ma…
arXiv:2610.16538v1 Announce Type: cross Abstract: We present PatTransBench, a 12,000-item Chinese-English/Japanese/Korean patent machine translation (PatMT) benchmark with a four-dimensional evaluation protocol.
arXiv:2610.16545v1 Announce Type: cross Abstract: Feature caching has become a mainstream training-free strategy for accelerating video diffusion models by reusing intermediate outputs across denoising steps.
arXiv:2610.16596v1 Announce Type: cross Abstract: Seizure prediction and detection, essential for clinical treatment of epilepsy, remain the crucial task of this neurological disease.
arXiv:2610.16627v1 Announce Type: cross Abstract: Existing human-centred XAI research predominantly evaluates explanations after they have been generated.
arXiv:2610.16632v1 Announce Type: cross Abstract: Memory-based long-video generation aims to combine user control with long-range visual consistency.
arXiv:2610.16636v1 Announce Type: cross Abstract: State space models provide efficient linear-complexity processing for long sequences, but their performance frequently degrades as context length grows.
arXiv:2610.16645v1 Announce Type: cross Abstract: Recovering divergence-free velocity fields from sparse and corrupted observations requires reconciling physical consistency, expressive representations, and robustness to…
arXiv:2610.16694v1 Announce Type: cross Abstract: Adversarial detection on evolving attributed graphs faces two challenges: fraud labels arrive late or not at all, and natural distributional drift erodes any trained deci…
arXiv:2610.16745v1 Announce Type: cross Abstract: Attention sinks are usually studied after they have formed.
arXiv:2610.16784v1 Announce Type: cross Abstract: Generating and editing presentation slides requires models to combine accurate text rendering, instruction following, visual grounding, aesthetic design, and precise edit…
arXiv:2610.16790v1 Announce Type: cross Abstract: Language model APIs can expose token-specific biases while withholding logits and token probabilities.
arXiv:2610.16814v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as judges to assign scalar scores that drive downstream decision-making, including tasks such as paper review and recom…
arXiv:2610.16817v1 Announce Type: cross Abstract: Progressive depth growth builds large networks by starting with shallow models and inserting layers during training.
arXiv:2610.16822v1 Announce Type: cross Abstract: Architecture attribute predictors reduce the cost of neural architecture search by estimating accuracy or latency from a small set of evaluated candidates.
arXiv:2610.16826v1 Announce Type: cross Abstract: Deepfake speech detectors are typically evaluated as binary classifiers on fixed benchmarks, but deployed systems face evolving attacks, codecs, speakers, and recording c…
arXiv:2610.16840v1 Announce Type: cross Abstract: Real-world systems often serve many objectives but can deploy only a few options, whose performance must be learned from noisy feedback.
arXiv:2610.16925v1 Announce Type: cross Abstract: Keeling et al.
arXiv:2610.16940v1 Announce Type: cross Abstract: Nearest neighbor search algorithms are widely used and have a long history, but we find that key implementation details are seldom reviewed in articles about them.
arXiv:2610.16957v1 Announce Type: cross Abstract: Standard hate speech detection datasets often emphasize explicit harmful language, but directed harm can also be expressed indirectly, without clearly hateful wording.
arXiv:2610.16967v1 Announce Type: cross Abstract: Physical AI is commonly formulated around an explicitly specified task: given a goal or instruction, a system perceives, reasons, and acts.
arXiv:2610.16977v1 Announce Type: cross Abstract: Visual in-context learning (ICL) enables vision-language models (VLMs) to adapt at test time via demonstration examples, but its effectiveness depends critically on the e…
arXiv:2610.16979v1 Announce Type: cross Abstract: Generative retrieval (GR) offers a promising paradigm for industrial search by unifying candidate generation within an autoregressive framework.
arXiv:2610.16984v1 Announce Type: cross Abstract: Offline reinforcement learning aims to learn effective policies from fixed datasets without environment interaction.
arXiv:2610.17002v1 Announce Type: cross Abstract: Large language models are trained on collections that may include scholarly works, while authors generally lack work-level information about whether and how their works w…
arXiv:2610.17014v1 Announce Type: cross Abstract: Functional brain connectome represents neural connectivity as a matrix of pairwise interactions between brain regions.
arXiv:2610.17029v1 Announce Type: cross Abstract: Neural operator splitting composes a library of neural operators, one per physical mechanism, into zero-shot simulators of new equations.
arXiv:2610.17062v1 Announce Type: cross Abstract: We propose a mitigation to reward hacking in reinforcement learning.
arXiv:2610.17085v1 Announce Type: cross Abstract: On many estimates, artificial general intelligence (AGI) is likely to emerge within the next few decades or even sooner.
arXiv:2610.17110v1 Announce Type: cross Abstract: AI-assisted research leaves instructions, computations, artifact revisions and checks whose relationships matter when another researcher receives the work.
arXiv:2610.17113v1 Announce Type: cross Abstract: Information extraction models often perform well on the datasets they are trained on, but transferring to new domains and annotation guidelines remains challenging.
arXiv:2610.17131v1 Announce Type: cross Abstract: Dynamic spatial audio reasoning requires a model to associate changing acoustic observations with the correct source and recover its spatial state at a queried time or in…
arXiv:2610.17161v1 Announce Type: cross Abstract: Teleoperation is widely used to collect high-quality demonstrations for robot learning.
arXiv:2610.17174v1 Announce Type: cross Abstract: Achieving complex, long-horizon robot behavior remains challenging because successful execution depends on skills grounded in a robot's physical affordances.
arXiv:2610.17191v1 Announce Type: cross Abstract: Linear-time sequence models typically store long-context information in a recurrent state.
arXiv:2610.17197v1 Announce Type: cross Abstract: In the age of "Software 3.0", when a complete program can be rewritten in minutes by an agent, the traditional approach of relying on code as the sole source of truth bec…
arXiv:2610.17221v1 Announce Type: cross Abstract: Neural surrogates for Partial Differential Equations (PDEs) are usually trained on synthetic data from numerical simulators.
arXiv:2610.17243v1 Announce Type: cross Abstract: The original EneMonIE proposal describes a Web-based semantic system for continuously monitoring energy trends through targeted information extraction from heterogeneous…
arXiv:2610.17269v1 Announce Type: cross Abstract: Learning symmetries through data augmentation offers an alternative to architectural equivariance, but does not guarantee that a network respects those symmetries.
arXiv:2610.17281v1 Announce Type: cross Abstract: SE(3)-equivariance provides a useful geometric inductive bias for visuomotor policies, encoding that actions covary with rigid transformations of the observation.
arXiv:2610.17314v1 Announce Type: cross Abstract: Deep learning has become the dominant form of machine learning due in part, to its ability to automatically engineer complex meta features from data.
arXiv:2610.17324v1 Announce Type: cross Abstract: AI-generated outputs are frequently perceived as highly creative, but also tend to be more similar to each other (homogenized) than human ideas.
arXiv:2610.17347v1 Announce Type: cross Abstract: We revisit the statistical mechanics of Transformer attention via modern Hopfield models.
arXiv:2610.17354v1 Announce Type: cross Abstract: Current evaluation protocols for medical image segmentation remain largely anchored in sample-wise comparisons, e.g., Dice and Hausdorff distance, which require each pred…
arXiv:2610.17358v1 Announce Type: cross Abstract: Formal verification proves that a program satisfies its specification, but says nothing about whether the specification captures what the author meant.
arXiv:2610.17368v1 Announce Type: cross Abstract: Generative recommendation models have shown promising results by representing items as semantic IDs and generating these IDs autoregressively.