Researchers propose D2PO, a framework that optimizes diffusion sampling policies by reformulating sampler optimization as a preference-based alignment problem using Direct Preference Optimization (DPO…
Amazon Web Services introduced Reverse Direct Preference Optimization (rDPO), a novel unlearning technique behind Amazon Nova Customizable Content Moderation Settings (CCMS), which allows approved cus…
Researchers at arXiv propose a framework for selecting the most informative comparison pairs in preference-based post-training of large language models, showing that strategic pair selection can impro…
Researchers have developed a method called Emergent Alignment that enables large language models to self-correct unethical outputs by adding a conscience step and using Direct Preference Optimization.…
A comprehensive review published on arXiv examines fine-tuning techniques for Large Language Models (LLMs), covering methodologies from supervised and unsupervised learning to parameter-efficient meth…
Researchers Liu et al. published a paper on arXiv 2025 introducing ProRL, a method using prolonged reinforcement learning with KL resets to expand reasoning boundaries in AI models. An interactive vis…
Researchers led by Damani et al. introduced a method to train language models to express their uncertainty by adding a calibration reward to reinforcement learning from verifiable rewards (RLVR). The …
Zhao et al. published GenPRM, a generative process reward model that reasons and runs code to verify each step, achieving state-of-the-art performance where a 7B parameter model outperforms a 72B para…
Researchers have identified three systematic failure modes in Audio LLMs when transcribing English-Mandarin code-switching speech: language omission, translation-instead-of-transcription, and hallucin…