Stay updated with the latest research and technology news
arXiv:2512.13980v2 Announce Type: replace Abstract: This paper proposes a structure-aware decoding method based on large language models to address the difficulty of traditional approaches in...
arXiv:2512.14549v2 Announce Type: replace Abstract: This paper combines autoregressive and masked-diffusion training objectives without any architectural modifications, resulting in flexible language models that outperform single-objective...
arXiv:2512.15036v2 Announce Type: replace Abstract: In real-world applications with large state and action spaces, reinforcement learning (RL) typically employs function approximations to represent core components...
arXiv:2512.15211v3 Announce Type: replace Abstract: Infrared and visible image fusion (IVIF) is a pivotal technology in low-altitude Unmanned Aerial Vehicle (UAV) reconnaissance missions, enabling robust...
arXiv:2512.16468v3 Announce Type: replace Abstract: Virtual testing using synthetic data has become a cornerstone of autonomous vehicle (AV) safety assurance. Despite progress in improving visual...
arXiv:2512.16687v2 Announce Type: replace Abstract: Text classification problems, such as gender classification from a blog, have been a well-matured research area that has been well...
arXiv:2512.17452v3 Announce Type: replace Abstract: Long-context LLM inference is bottlenecked by the quadratic attention complexity and linear KV cache growth. Prior approaches mitigate this via...
arXiv:2512.17843v3 Announce Type: replace Abstract: While academic research typically treats Large Language Models (LLM) as generic text generators, they are distinct commercial products with unique...
arXiv:2512.18901v3 Announce Type: replace Abstract: We present Gabliteration, a novel neural weight modification technique that advances beyond traditional abliteration methods by implementing adaptive multi-directional projections...
arXiv:2512.18928v2 Announce Type: replace Abstract: This work puts forward a novel nonlinear optimal filter namely the Ensemble Schr{\"o}dinger Bridge nonlinear filter. The proposed filter finds...
arXiv:2512.19171v3 Announce Type: replace Abstract: Current autoregressive language models couple high-level reasoning and low-level token generation into a single sequential process, making the reasoning trajectory...
arXiv:2512.19920v3 Announce Type: replace Abstract: LLM deployment in critical domains is currently impeded by persistent hallucinations--generating plausible but factually incorrect assertions. While scaling laws drove...
arXiv:2512.20573v3 Announce Type: replace Abstract: Diffusion Large Language Models (dLLMs) offer fast, parallel token generation, but their standalone use is plagued by an inherent efficiency-quality...
arXiv:2512.22131v2 Announce Type: replace Abstract: Stochastic computing (SC) offers significant reductions in hardware complexity for traditional convolutional neural networks(CNNs). However, despite its advantages, stochastic computing...
arXiv:2512.22471v3 Announce Type: replace Abstract: Transformers often appear to perform Bayesian reasoning in context, but verifying this rigorously has been impossible: natural data lack analytic...
arXiv:2512.23066v2 Announce Type: replace Abstract: Grey literature is essential to software engineering research as it captures practices and decisions that rarely appear in academic venues....
arXiv:2512.23340v2 Announce Type: replace Abstract: Recent advances in large language models (LLMs) have been largely driven by scaling laws for individual models, which predict performance...
arXiv:2512.23565v5 Announce Type: replace Abstract: The integration of Multimodal Large Language Models (MLLMs) into chemistry promises to revolutionize scientific discovery, yet their ability to comprehend...
arXiv:2512.23752v3 Announce Type: replace Abstract: Recent work has shown that small transformers trained in controlled "wind-tunnel'' settings can implement exact Bayesian inference, and that their...
arXiv:2512.23880v2 Announce Type: replace Abstract: Large language model (LLM) agents currently depend on predefined tools or early-stage tool generation, limiting their adaptability and scalability to...
arXiv:2512.24601v2 Announce Type: replace Abstract: We study allowing large language models (LLMs) to process arbitrarily long prompts through the lens of inference-time scaling. We propose...
arXiv:2601.00269v2 Announce Type: replace Abstract: Faithfulness hallucinations in VQA occur when vision-language models produce fluent yet visually ungrounded answers, severely undermining their reliability in safety-critical...
arXiv:2601.00533v2 Announce Type: replace Abstract: All-in-one image restoration aims to recover clean images from diverse unknown degradations using a single model. But extending this task...
arXiv:2601.01294v2 Announce Type: replace Abstract: We study timbre transfer as an inference-time editing problem for music audio. Starting from a strong pre-trained latent diffusion model,...