AIConfPaper
← Search

Zeming Chen

13 accepted papers

2026

Mixture of Cognitive Reasoners: Modular Reasoning with Brain-Like Specialization

Badr AlKhamissi, C. Nicolò De Sabbata, Greta Tuckute, Zeming Chen, Martin Schrimpf, Antoine Bosselut
ICLR 2026poster

Human cognitive behavior arises from the interaction of specialized brain networks dedicated to distinct functions, such as language, logic, and social reasoning. Inspired by this organization, we propose Mixture of Cognitive Reasoners (MiCRo): a modular, transformer-based architecture post-trained…

Cited by 0Source ↗code ↗Scholar ↗
2026

PERK: Long-Context Reasoning as Parameter-Efficient Test-Time Learning

Zeming Chen, Angelika Romanou, Gail Weiss, Antoine Bosselut
ICLR 2026poster

Long-context reasoning requires accurately identifying relevant information in extensive, noisy input contexts. In this work, we propose PERK (Parameter Efficient Reasoning over Knowledge), a scalable approach for learning to encode long contexts using gradient updates at test time. Specifically, PE…

Cited by 0Source ↗Scholar ↗
2026

Schema-Guided World Modeling for Understanding Hierarchical Visual Dynamics

Silin Gao, Hao Zhao, Zeming Chen, Sepideh Mamooler, Antara R Bhattacharya, Qiyu Wu +5
ICML 2026poster

Multimodal LLMs lack a systematic understanding of visual dynamics in complex human world activities, which requires the model to predict or simulate multiple levels of dynamic constituents, such as the general progression of actions and the associated changes of low-level details in the world. To a…

Cited by 0Source ↗Scholar ↗
2025

Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation

Qiyue Gao, Xinyu Pi, Kevin Liu, Junrong Chen, Ruolan Yang, Xinqi Huang +18
ACL 2025finding

Internal world models (WMs) enable agents to understand the world’s state and predict transitions, serving as the basis for advanced deliberative reasoning.Recent large Vision-Language Models (VLMs), such as GPT-4o and Gemini, exhibit potential as general-purpose WMs. While the latest studies have e…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

GeoExplorer: Active Geo-localization with Curiosity-Driven Exploration

Li Mi, Manon Béchaz, Zeming Chen, Antoine Bosselut, Devis Tuia
ICCV 2025poster

Active Geo-localization (AGL) is the task of localizing a goal, represented in various modalities (e.g., aerial images, ground-level images, or text), within a predefined search area. Current methods approach AGL as a goal-reaching reinforcement learning (RL) problem with a distance-based reward. Th…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge

Angelika Romanou, Negar Foroutan, Anna Sotnikova, Sree Harsha Nelaturu, Shivalika Singh, Rishabh Maheshwary +51
ICLR 2025spotlight

The performance differential of large language models (LLM) between languages hinders their effective deployment in many regions, inhibiting the potential economic and societal value of generative AI tools in many communities. However, the development of functional LLMs in many languages (i.e., mult…

Cited by 9Source ↗PDF ↗Scholar ↗
2024

Complex Reasoning over Logical Queries on Commonsense Knowledge Graphs

Tianqing Fang, Zeming Chen, Yangqiu Song, Antoine Bosselut
ACL 2024long

Event commonsense reasoning requires the ability to reason about the relationship between events, as well as infer implicit contextunderlying that relationship. However, data scarcity makes it challenging for language models to learn to generate commonsense infer-ences for contexts and questions inv…

Cited by 10Source ↗PDF ↗code ↗Scholar ↗
2024

Discovering Knowledge-Critical Subnetworks in Pretrained Language Models

Deniz Bayazit, Negar Foroutan, Zeming Chen, Gail Weiss, Antoine Bosselut
EMNLP 2024main

Pretrained language models (LMs) encode implicit representations of knowledge in their parameters. However, localizing these representations and disentangling them from each other remains an open problem. In this work, we investigate whether pretrained language models contain various *knowledge-crit…

Cited by 19Source ↗PDF ↗code ↗Scholar ↗
2023

DISCO: Distilling Counterfactuals with Large Language Models

Zeming Chen, Qiyue Gao, Antoine Bosselut, Ashish Sabharwal, Kyle Richardson
ACL 2023long

Models trained with counterfactually augmented data learn representations of the causal structure of tasks, enabling robust generalization. However, high-quality counterfactual data is scarce for most tasks and not easily generated at scale. When crowdsourced, such data is typically limited in scale…

Cited by 75Source ↗PDF ↗code ↗Scholar ↗
2023

RECKONING: Reasoning through Dynamic Knowledge Encoding

Zeming Chen, Gail Weiss, Eric Mitchell, Asli Celikyilmaz, Antoine Bosselut
NeurIPS 2023poster

Recent studies on transformer-based language models show that they can answer questions by reasoning over knowledge provided as part of the context (i.e., in-context reasoning). However, since the available knowledge is often not filtered for a particular question, in-context reasoning can be sensit…

Cited by 12Source ↗PDF ↗Scholar ↗
2022

Curriculum: A Broad-Coverage Benchmark for Linguistic Phenomena in Natural Language Understanding

Zeming Chen, Qiyue Gao
NAACL 2022long

In the age of large transformer language models, linguistic evaluation play an important role in diagnosing models’ abilities and limitations on natural language understanding. However, current evaluation methods show some significant shortcomings. In particular, they do not provide insight into how…

Cited by 8Source ↗PDF ↗code ↗Scholar ↗
2022

Probing Linguistic Information for Logical Inference in Pre-trained Language Models

Zeming Chen, Qiyue Gao
AAAI 2022technical

Progress in pre-trained language models has led to a surge of impressive results on downstream tasks for natural language understanding. Recent work on probing pre-trained language models uncovered a wide range of linguistic properties encoded in their contextualized representations. However, it is…

Cited by 9Source ↗PDF ↗code ↗Scholar ↗