8 papers
Rational ANOVA Networks
Jusheng Zhang, Ningyuan Liu, Qinhan Lyu +2
Deep neural networks typically treat nonlinearities as fixed primitives (e.g., ReLU), limiting both interpretability and the granularity of control over the induced function class.…
Self-Rewarded Multimodal Coherent Reasoning Across Diverse Visual Domains
Jesen Zhang, Ningyuan Liu, Kaitong Cai +5
Multimodal LLMs often produce fluent yet unreliable reasoning, exhibiting weak step-to-step coherence and insufficient visual grounding, largely because existing alignment approach…
RevFFN: Memory-Efficient Full-Parameter Fine-Tuning of Mixture-of-Experts LLMs with Reversible Blocks
Ningyuan Liu, Jing Yang, Kaitong Cai +1
Full parameter fine tuning is a key technique for adapting large language models (LLMs) to downstream tasks, but it incurs substantial memory overhead due to the need to cache exte…
LLM-CAS: Dynamic Neuron Perturbation for Real-Time Hallucination Correction
Jensen Zhang, Ningyuan Liu, Yijia Fan +5
Large language models (LLMs) often generate hallucinated content that lacks factual or contextual grounding, limiting their reliability in critical applications. Existing approache…
GTMA: Dynamic Representation Optimization for OOD Vision-Language Models
Jensen Zhang, Ningyuan Liu, Keze Wang
Vision-language models (VLMs) struggle in open-world applications, where out-of-distribution (OOD) concepts often trigger cross-modal alignment collapse and severely degrade zero-s…
Failure-Driven Workflow Refinement
Jusheng Zhang, Kaitong Cai, Qinglin Zeng +4
Optimizing LLM-based workflows is typically formulated as a global search, where candidate workflows are evaluated based on a scalar metric. This paradigm, however, suffers from a…
MAT-Agent: Adaptive Multi-Agent Training Optimization
Jusheng Zhang, Kaitong Cai, Yijia Fan +2
Multi-label image classification demands adaptive training strategies to navigate complex, evolving visual-semantic landscapes, yet conventional methods rely on static configuratio…
KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems
Jusheng Zhang, Zimeng Huang, Yijia Fan +6
As scaling large language models faces prohibitive costs, multi-agent systems emerge as a promising alternative, though challenged by static knowledge assumptions and coordination…