arXiv:2512.14806v4 Announce Type: replace-cross Abstract: Artificial Intelligence (AI) is beginning to transform the research process by automating the discovery of new solutions. This shift depends on the availability of reliable verifiers, which AI-driven approaches require to validate candidate solutions. Research focused on improving systems performance is especially well-suited to this paradigm because system performance problems […]
Context-Aware Initialization for Reducing Generative Path Length in Diffusion Language Models
arXiv:2512.19004v1 Announce Type: cross Abstract: Diffusion Large Language Models (DLLMs) enable fully parallel token decoding but often remain impractical at inference time due to the many denoising iterations required to refine an information-free, fully masked initialization into coherent text. Most existing acceleration methods focus on traversing this generative trajectory more efficiently via improved solvers or […]
Self-Attention with State-Object Weighted Combination for Compositional Zero Shot Learning
arXiv:2512.18969v1 Announce Type: cross Abstract: Object recognition has become prevalent across various industries. However, most existing applications are limited to identifying objects alone, without considering their associated states. The ability to recognize both the state and object simultaneously remains less common. One approach to address this is by treating state and object as a single […]
Inferring Latent Market Forces: Evaluating LLM Detection of Gamma Exposure Patterns via Obfuscation Testing
arXiv:2512.17923v1 Announce Type: cross Abstract: We introduce obfuscation testing, a novel methodology for validating whether large language models detect structural market patterns through causal reasoning rather than temporal association. Testing three dealer hedging constraint patterns (gamma positioning, stock pinning, 0DTE hedging) on 242 trading days (95.6% coverage) of S&P 500 options data, we find LLMs […]
FedVideoMAE: Efficient Privacy-Preserving Federated Video Moderation
arXiv:2512.18809v1 Announce Type: cross Abstract: The rapid growth of short-form video platforms increases the need for privacy-preserving moderation, as cloud-based pipelines expose raw videos to privacy risks, high bandwidth costs, and inference latency. To address these challenges, we propose an on-device federated learning framework for video violence detection that integrates self-supervised VideoMAE representations, LoRA-based parameter-efficient […]
CORE: Concept-Oriented Reinforcement for Bridging the Definition-Application Gap in Mathematical Reasoning
arXiv:2512.18857v1 Announce Type: new Abstract: Large language models (LLMs) often solve challenging math exercises yet fail to apply the concept right when the problem requires genuine understanding. Popular Reinforcement Learning with Verifiable Rewards (RLVR) pipelines reinforce final answers but provide little fine-grained conceptual signal, so models improve at pattern reuse rather than conceptual applications. We […]
Training Multimodal Large Reasoning Models Needs Better Thoughts: A Three-Stage Framework for Long Chain-of-Thought Synthesis and Selection
arXiv:2512.18956v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) have demonstrated remarkable performance on complex reasoning tasks through long Chain-of-Thought (CoT) reasoning. Extending these successes to multimodal reasoning remains challenging due to the increased complexity of integrating diverse input modalities and the scarcity of high-quality long CoT training data. Existing multimodal datasets and CoT synthesis […]
KVReviver: Reversible KV Cache Compression with Sketch-Based Token Reconstruction
arXiv:2512.17917v1 Announce Type: cross Abstract: As the context length of current large language models (LLMs) rapidly increases, the memory demand for the Key-Value (KV) cache is becoming a bottleneck for LLM deployment and batch processing. Traditional KV cache compression methods typically involve permanently evicting or irreversibly merging “less important” tokens with low attention scores. This […]
Quantifying the Emergence of Selection Prior to Biological Evolution
arXiv:2512.18752v1 Announce Type: new Abstract: Selection is central to biological evolution, yet there has been no general experimental framework for quantifying selection in chemical systems before life. Here we demonstrate that selection in a prebiological chemical system can be directly quantified. Assembly Theory predicts that selection corresponds to a transition from undirected to directed exploration […]
Learning General Policies with Policy Gradient Methods
arXiv:2512.19366v1 Announce Type: new Abstract: While reinforcement learning methods have delivered remarkable results in a number of settings, generalization, i.e., the ability to produce policies that generalize in a reliable and systematic way, has remained a challenge. The problem of generalization has been addressed formally in classical planning where provable correct policies that generalize over […]