Boris Knyazev
Author directory2026
M^4olGen: Multi-Agent, Multi-Stage Molecular Generation under Precise Multi-Property Constraints
Yizhan Li | Florence Cloutier | Sifan Wu | Ali Parviz | Boris Knyazev | Yan Zhang | Glen Berseth | Bang Liu
Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
Yizhan Li | Florence Cloutier | Sifan Wu | Ali Parviz | Boris Knyazev | Yan Zhang | Glen Berseth | Bang Liu
Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
Generating molecules that satisfy precise numeric constraints over multiple physicochemical properties is critical and challenging. Although large language models (LLMs) are expressive, they struggle with precise multi-objective control and numeric reasoning without external structure and feedback. We introduce M^4olGen, a fragment-level, retrieval-augmented, two-stage framework for molecule generation under multi-property constraints. Stage I : Prototype generation: a multi-agent reasoner performs retrieval-anchored, fragment-level edits to produce a candidate near the feasible region. Stage II : RL-based fine-grained optimization: a fragment-level optimizer trained with Group Relative Policy Optimization (GRPO) applies one- or multi-hop refinements to explicitly minimize the property errors toward our target while regulating edit complexity and deviation from the prototype. A large, automatically curated dataset with reasoning chains of fragment edits and measured property deltas underpins both stages, enabling deterministic, reproducible supervision and controllable multi-hop reasoning. Unlike prior work, our framework better reasons about molecules by leveraging fragments and supports controllable refinement toward numeric targets. Experiments on generation under two sets of property constraints (QED, LogP, Molecular Weight and HOMO, LUMO) show consistent gains in validity and precise satisfaction of multi-property targets, outperforming strong LLMs and graph-based algorithms.
2025
(Almost) Free Modality Stitching of Foundation Models
Jaisidh Singh | Diganta Misra | Boris Knyazev | Antonio Orvieto
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
Jaisidh Singh | Diganta Misra | Boris Knyazev | Antonio Orvieto
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
Foundation multi-modal models are often designed by stitching of multiple existing pretrained uni-modal models: for example, an image classifier with a text model. This stitching process is performed by training a connector module that aims to align the representation spaces of these uni-modal models towards a multi-modal objective. However, given the complexity of training such connectors on large scale web-based datasets coupled with the ever-increasing number of available pretrained uni-modal models, the task of uni-modal models selection and subsequent connector module training becomes computationally demanding. To address this under-studied critical problem, we propose Hypernetwork Model Alignment (Hyma), a novel all-in-one solution for optimal uni-modal model selection and connector training by leveraging hypernetworks. Specifically, our framework utilizes the parameter prediction capability of a hypernetwork to obtain jointly trained connector modules for N × M combinations of uni-modal models. In our experiments, Hyma reduces the cost of searching for the best performing uni-modal model pair by 10×, while matching the ranking and trained connector performance obtained via grid search across a suite of diverse multi-modal benchmarks.
Search