1 citations · 2 across the 13 of their papers we have counts for
14 papers
EAU: Environment-Agent-User Co-evolution for Training User-Centric Agents
Min Cai, Dan Zhang, Gao Xing +3
Training LLM agents to interact with users over multiple turns is challenging because the learning signal depends not only on the agent, but also on the user simulator and environm…
Continual Learning in Transition
Zhiyan Hou, Dan Zhang, Tao Feng +11
Classical continual learning (CL) has primarily focused on enabling models to update and retain knowledge through parameter-centric mechanisms, e.g., training strategies, architect…
On-Policy Distillation with Curriculum Turn-level Guidance for Multi-turn Agents
Gengsheng Li, Mao Zheng, Mingyang Song +8
Multi-turn agents that plan, invoke tools, and interact with environments offer a promising paradigm for solving complex tasks, yet their capabilities typically rely on very large…
Re-evaluating Confidence Remasking in Masked Diffusion Language Models
Stipe Frkovic, Metod Jazbec, Dan Zhang +3
Masked diffusion language models (dLLMs) have recently emerged as a competitive alternative to autoregressive language models, with the promise of faster inference via parallel tok…
TRACE: Trajectory Risk-Aware Compression for Long-Horizon Agent Safety
Zhepei Hong, Lin Wang, Liting Li +5
Long-horizon LLM agents produce safety evidence across long trajectories, where sparse, delayed, and compositional risk signals often escape local moderation. Existing turn-level o…
UFO: A Unified Flow-Oriented Framework for Robust Continual Graph Learning
Danhui Zhang, Zhe Wang, Qing Qing +6
Graph learning research has increasingly shifted toward continual graph learning (CGL), which better reflects real-world scenarios where graphs evolve over time. However, existing…
Rubric-based On-policy Distillation
Junfeng Fang, Zhepei Hong, Mao Zheng +7
On-policy distillation (OPD) is a powerful paradigm for model alignment, yet its reliance on teacher logits restricts its application to white-box scenarios. We contend that struct…
Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
Gengsheng Li, Tianyu Yang, Junfeng Fang +6
Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for post-training large language models. While Group Relative Policy Optimization (GRPO) is wid…
NExT-Guard: Training-Free Streaming Safeguard without Token-Level Labels
Junfeng Fang, Nachuan Chen, Houcheng Jiang +5
Large language models are increasingly deployed in streaming scenarios, rendering conventional post-hoc safeguards ineffective as they fail to interdict unsafe content in real-time…
Generative Uncertainty in Diffusion Models
Metod Jazbec, Eliot Wong-Toi, Guoxuan Xia +3
Diffusion models have recently driven significant breakthroughs in generative modeling. While state-of-the-art models produce high-quality samples on average, individual samples ca…
Temporal Test-Time Adaptation with State-Space Models
Mona Schirmer, Dan Zhang, Eric Nalisnick
Distribution shifts between training and test data are inevitable over the lifecycle of a deployed model, leading to performance decay. Adapting a model on test samples can help mi…
Fast yet Safe: Early-Exiting with Risk Control
Metod Jazbec, Alexander Timans, Tin Hadži Veljković +4
Scaling machine learning models significantly improves their performance. However, such gains come at the cost of inference being slow and resource-intensive. Early-exit neural net…
Beyond Top-Class Agreement: Using Divergences to Forecast Performance under Distribution Shift
Mona Schirmer, Dan Zhang, Eric Nalisnick
Knowing if a model will generalize to data 'in the wild' is crucial for safe deployment. To this end, we study model disagreement notions that consider the full predictive distribu…
Early-Exit Neural Networks with Nested Prediction Sets
Metod Jazbec, Patrick Forré, Stephan Mandt +2
Early-exit neural networks (EENNs) enable adaptive and efficient inference by providing predictions at multiple stages during the forward pass. In safety-critical applications, the…