arXiv:2503.23972v4 Announce Type: replace-cross Abstract: The pursuit of energy-efficient and adaptive artificial intelligence (AI) has positioned neuromorphic computing as a promising alternative to conventional computing. However, achieving learning on these platforms requires techniques that prioritize local information while enabling effective credit assignment. Here, we propose noise-based reward-modulated learning (NRL), a novel synaptic plasticity rule that […]
From Aggregation to Selection: User-Validated Distributed Social Recommendation
arXiv:2505.21388v4 Announce Type: replace-cross Abstract: Social recommender systems facilitate social connections by identifying potential friends for users. Each user maintains a local social network centered around themselves, resulting in a naturally distributed social structure. Recent research on distributed modeling for social recommender systems has gained increasing attention, as it naturally aligns with the user-centric structure […]
MENTOR: Efficient Multimodal-Conditioned Tuning for Autoregressive Vision Generation Models
arXiv:2507.09574v2 Announce Type: replace-cross Abstract: Recent text-to-image models produce high-quality results but still struggle with precise visual control, balancing multimodal inputs, and requiring extensive training for complex multimodal image generation. To address these limitations, we propose MENTOR, a novel autoregressive (AR) framework for efficient Multimodal-conditioned Tuning for Autoregressive multimodal image generation. MENTOR combines an AR […]
Memorization in Large Language Models in Medicine: Prevalence, Characteristics, and Implications
arXiv:2509.08604v4 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated significant potential in medicine, with many studies adapting them through continued pre-training or fine-tuning on medical data to enhance domain-specific accuracy and safety. However, a key open question remains: to what extent do LLMs memorize medical training data. Memorization can be beneficial when it […]
Probing the Hidden Talent of ASR Foundation Models for L2 English Oral Assessment
arXiv:2510.16387v2 Announce Type: replace-cross Abstract: In this paper, we explore the untapped potential of Whisper, a well-established automatic speech recognition (ASR) foundation model, in the context of L2 spoken language assessment (SLA). Unlike prior studies that extrinsically analyze transcriptions produced by Whisper, our approach goes a step further to probe its latent capabilities by extracting […]
Multimodal Evaluation of Russian-language Architectures
arXiv:2511.15552v3 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) are currently at the center of research attention, showing rapid progress in scale and capabilities, yet their intelligence, limitations, and risks remain insufficiently understood. To address these issues, particularly in the context of the Russian language, where no multimodal benchmarks currently exist, we introduce MERA […]
Far from the Shallow: Brain-Predictive Reasoning Embedding through Residual Disentanglement
arXiv:2510.22860v3 Announce Type: replace-cross Abstract: Understanding how the human brain progresses from processing simple linguistic inputs to performing high-level reasoning is a fundamental challenge in neuroscience. While modern large language models (LLMs) are increasingly used to model neural responses to language, their internal representations are highly “entangled,” mixing information about lexicon, syntax, meaning, and reasoning. […]
RRPO: Robust Reward Policy Optimization for LLM-based Emotional TTS
arXiv:2512.04552v2 Announce Type: replace-cross Abstract: Differentiable reinforcement learning (RL) frameworks like DiffRO offer a powerful approach for controllable text-to-speech (TTS), but are vulnerable to reward hacking, particularly for nuanced tasks like emotion control. The policy model can exploit a vanilla Reward Model (RM) by generating acoustic artifacts to achieve spurious rewards, but at the cost […]
Single-Pixel Vision-Language Model for Intrinsic Privacy-Preserving Behavioral Intelligence
arXiv:2601.17050v1 Announce Type: cross Abstract: Adverse social interactions, such as bullying, harassment, and other illicit activities, pose significant threats to individual well-being and public safety, leaving profound impacts on physical and mental health. However, these critical events frequently occur in privacy-sensitive environments like restrooms, and changing rooms, where conventional surveillance is prohibited or severely restricted […]
MathMixup: Boosting LLM Mathematical Reasoning with Difficulty-Controllable Data Synthesis and Curriculum Learning
arXiv:2601.17006v1 Announce Type: cross Abstract: In mathematical reasoning tasks, the advancement of Large Language Models (LLMs) relies heavily on high-quality training data with clearly defined and well-graded difficulty levels. However, existing data synthesis methods often suffer from limited diversity and lack precise control over problem difficulty, making them insufficient for supporting efficient training paradigms such […]
Data-Efficient Meningioma Segmentation via Implicit Spatiotemporal Mixing and Sim2Real Semantic Injection
arXiv:2601.17031v1 Announce Type: cross Abstract: The performance of medical image segmentation is increasingly defined by the efficiency of data utilization rather than merely the volume of raw data. Accurate segmentation, particularly for complex pathologies like meningiomas, demands that models fully exploit the latent information within limited high-quality annotations. To maximize the value of existing datasets, […]
FadeMem: Biologically-Inspired Forgetting for Efficient Agent Memory
arXiv:2601.18642v1 Announce Type: new Abstract: Large language models deployed as autonomous agents face critical memory limitations, lacking selective forgetting mechanisms that lead to either catastrophic forgetting at context boundaries or information overload within them. While human memory naturally balances retention and forgetting through adaptive decay processes, current AI systems employ binary retention strategies that preserve […]