We have 8 of 22 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.
Compact OCR-specific vision-language models achieve strong document parsing performance, but often rely on costly supervision and focus primarily on visual-text reconstruction. We introduce Xiaomi-OCR-0, a unified 0.8B model for document parsing and OCR-centric understanding. We build an approximately 170M-sample OCR-c...
This work identifies a systematic upstream/downstream structure in dLLM rollouts and proposes Informed Masking (IM), which derives a per-token priority score from the denoising trajectory at zero extra inference cost and biases mask sampling toward downstream tokens.
The MaP is proposed, a unified framework that seamlessly harmonizes divergent GUI navigation tasks and effectively mitigates gradient conflicts and significantly outperforms the direct mixture training, establishing a robust paradigm for multi-task GUI navigation.
DAREBench (Deployment-Aware and Reliable Evaluation of Models as Agents), a benchmark designed to capture workload variation and support reliable agent evaluation, is introduced, suggesting that agent deployment and model selection should consider workload profiles, deployment mode, and accuracy--cost trade-offs rather...
This work proposes NTEP-R (NTEP Reward), a supervision mechanism ensuring that each tool invocation strictly advances the reasoning process toward the final solution, and introduces a non-repeated-goal regularizer to penalize redundant calls that revisit satisfied NTEP goals.
Switch-Reasoner is proposed, a GRPO-based framework that learns to adaptively select reasoning modes for MLLMs and introduces a dual-level regulation mechanism that balances the overall use of Thinking Mode and Direct Mode while providing sample-level supervision based on the relative benefit of the two choices.
DeltaV is proposed, a ULMM that replaces full-image generation with visual updates and introduces a temporal similarity (TSIM) Router, which stops allocating tokens once the marginal reconstruction gain falls below a threshold.
This work studies reference-free post-training for multilingual machine translation with open large language models and finds that on-policy distillation reaches, but does not surpass, the quality frontier achieved by RL with checkpoint interpolation.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
