We have 5 of 13 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
This work forms data rewriting as a policy-learning problem and trains a lightweight LoRA rewriting policy with reinforcement learning that optimizes question-answering-style distributional alignment and semantic diversity under a hard task-consistency gate, producing verified supervision for downstream SFT.
This work focuses on a continuation-triggered jailbreak phenomenon, whereby simply relocating a continuation-triggered instruction suffix can substantially increase jailbreak success rates and proposes Head Competition Steering (HCS), a mechanistically grounded inference-time strategy that explicitly leverages the comp...
GAS is presented, a generation-guided training framework that reinterprets visual generation as auxiliary supervision for representation learning and improves aggregate multimodal understanding, with its most reliable gains on perception and spatial comprehension.
The DecoupleMix framework delivers two critical capabilities: guiding what data to collect next and rendering dataset validation a controlled, attributable experiment, and is competitive with strong open-source models trained with substantially larger multimodal budgets.
This work proposes PRISM, a four-stage data synthesis framework that produces persona--task pairs, prefix-guided rule sets, quality-filtered rubrics, and structured verification traces, and introduces PRISM-Eval, whose Loose and Strict metrics use deterministic matching against fixed labels and therefore require no inf...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
