Skip to content

Author

Yulia Tsvetkov

We have 6 of 43 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.

#natural language process... Preprint Oct 2026

Reading, Not Manipulating: Leveraging Router Logits for Multimodal Safety in MoE Vision-Language Models

Vision-language models (VLMs) face compositional safety risks where harmful intent emerges from the interaction between visual and textual inputs. As mixture-of-experts (MoE) VLMs become increasingly common, recent work has explored various safety interventions, including prompting, supervised fine-tuning, and routing-...

Zi-Yuan Yang, Wen-Xuan Ding, Shang-Bin Feng et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Multi-LLM Collaborative Alignment via Stackelberg Games

A pool of language models can collaborate and improve collectively by learning from one another's responses. These interactions depend on the instructions used during training. Existing methods typically sample instructions uniformly, even though their usefulness may change as the models improve: an instruction on whic...

Christina Hahn, Shang-Bin Feng, Dean Light et al. · 0 citations

Save Your Saturated Data: Learning Beyond Reward Saturation in Group-Based RL

This work studies interventions at four levels of group-policy RL pipelines---data, rollout, reward, and advantage---and conducts extensive RL training on saturated reasoning data only, demonstrating that don't waste your saturated data: with the right strategies they can be recycled into useful RL training signals in...

Zi-Yuan Yang, Yike Wang, Shang-Bin Feng et al. · 0 citations
Jul 2026

Rethinking the Evaluation of Harness Evolution for Agents

An extensive evaluation of automatic harness evolution for LLM agents is conducted, comparing harness evolution with simple test-time scaling and discovery baselines under comparable feedback and inference budgets, and also evaluating evolved harnesses on held-out tasks to assess whether the discovered improvements gen...

Yike Wang, Huaisheng Zhu, Zhengyu Hu et al. · 18 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.