Context Language Models

Context language models treat context as self-modified files to learn context management, outperforming external strategies with lower compute and enabling in-context and parametric learning of management strategies.

Rulin Shao, Shannon Zejiang Shen, Junjie Oscar Yin, Yuetai Li and 9 more

Published Sep 29, 2026 · 0 citations · ▲ 43 on Hugging Face · Code ★ 595

TeacherGRPO: Closing the Capacity Gap in Reasoning Distillation via Teacher Alignment

TeacherGRPO aligns teachers to student distributions via reinforcement learning to overcome reasoning distillation's Gap Curse and improves student performance.

Zhenyu Lei, Zihan Chen, Yaochen Zhu, Shangbin Feng and 4 more

Published Aug 20, 2026 · 0 citations

Scaling Participation in Modular AI Systems

Modular participatory AI combines small stakeholder-trained models into compositional systems that outperform monolithic LLMs by up to 15.4% and exhibit emergent collaborative capabilities.

Shangbin Feng, Yike Wang, Weijia Shi, Luke Zettlemoyer and 2 more

Published Jun 5, 2026 · 0 citations

MoCo: A One-Stop Shop for Model Collaboration Research

MoCo unifies 26 model collaboration methods and 25 benchmarks to show collaboration outperforms single models in 61% of settings by up to 25.8%.

Shangbin Feng, Yuyang Bai, Ziyuan Yang, Yike Wang and 16 more

Published Jan 29, 2026 · 0 citations · Code ★ 63

When One LLM Drools, Multi-LLM Collaboration Rules

Multi-LLM collaboration outperforms single LLM reasoning on tasks where individual models fail, demonstrating collective rule over solo drooling.

Shangbin Feng, Wenxuan Ding, Alisa Liu, Zifeng Wang and 9 more

Published 2026 · 1 citation

Instruction Tuning for Large Language Models: A Survey

Instruction tuning surveys supervised fine-tuning of LLMs on instruction-output pairs to align next-word prediction with human intent, covering datasets, training, applications, and limitations.

Shengyu Zhang, Linfeng Dong, Xiaoya Li, Sen Zhang and 7 more

Published Nov 17, 2025 · 79 citations

Biased LLMs can Influence Political Decision-Making

Biased LLMs influence political decision-making, altering judgments and choices in simulated policy scenarios with measurable partisan effects.

Jillian Fisher, Shangbin Feng, Robert Aron, Thomas Richardson and 5 more

Published 2025 · 13 citations

Stronger Models are NOT Stronger Teachers for Instruction Tuning

Stronger models are not stronger teachers for instruction tuning due to teacher-student incompatibility; a compatibility-adjusted reward metric predicts effective generators.

Zhangchen Xu, Fengqing Jiang, Luyao Niu, Lin, Bill Yuchen and 1 more

Published Nov 11, 2024 · 0 citations · ▲ 39 on Hugging Face

Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only

LLMs distinguish degrees of wrongness among incorrect answers, and alignment with such preferences yields less wrong answers and better calibration.

Jihan Yao, Wenxuan Ding, Shangbin Feng, Lucy Lu Wang and 1 more

Published Oct 14, 2024 · 0 citations · Code ★ 10

What Does the Bot Say? Opportunities and Risks of Large Language Models in Social Media Bot Detection

Instruction-tuned LLMs with a mixture-of-experts framework outperform bot detectors by 9.1%, but LLM-guided manipulation reduces their performance by up to 29.6%.

Shangbin Feng, Herun Wan, Ningnan Wang, Zhaoxuan Tan and 2 more

Published 2024 · 27 citations

P3Sum: Preserving Author’s Perspective in News Summarization with Diffusion Language Models

P3Sum uses diffusion language models to preserve authorial perspective in news summarization, outperforming autoregressive baselines on perspective fidelity.

Yuhan Liu, Shangbin Feng, Xiaochuang Han, Vidhisha Balachandran and 3 more

Published 2024 · 2 citations

Don’t Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration

Multi-LLM collaboration detects knowledge gaps to make LLMs abstain from wrong answers instead of hallucinating.

Shangbin Feng, Weijia Shi, Yike Wang, Wenxuan Ding and 2 more

Published 2024 · 37 citations

Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration

Modular Pluralism plugs specialized community LMs into base LLMs to enable Overton, steerable, and distributional pluralistic alignment across diverse communities.

Shangbin Feng, Taylor Sorensen, Yuhan Liu, Jillian Fisher and 3 more

Published 2024 · 15 citations

Teaching LLMs to Abstain across Languages via Multilingual Feedback

Multilingual feedback teaches LLMs to abstain from answering in low-resource languages and improves cross-lingual abstention without degrading performance.

Shangbin Feng, Weijia Shi, Yike Wang, Wenxuan Ding and 5 more

Published 2024 · 4 citations

BotPercent: Estimating Bot Populations in Twitter Communities

BotPercent estimates community-specific Twitter bot populations by calibrating detection models across social contexts, revealing heterogeneous spatial-temporal bot distributions and achieving state-of-the-art community-level detection accuracy.

Zhaoxuan Tan, Shangbin Feng, Melanie Sclar, Herun Wan and 3 more

Published 2023 · 16 citations

From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models

Pretraining data political biases propagate through language models into unfair hate speech and misinformation detectors, reinforcing polarization.

Shangbin Feng, Chan Young Park, Yuhan Liu, Yulia Tsvetkov

Published 2023 · 138 citations

BIC: Twitter Bot Detection with Text-Graph Interaction and Semantic Consistency

BIC detects Twitter bots via text-graph interaction and semantic consistency modeling, achieving high detection accuracy.

Zhenyu Lei, Herun Wan, Wenqian Zhang, Shangbin Feng and 4 more

Published 2023 · 35 citations

TwiBot-22: Towards Graph-Based Twitter Bot Detection

TwiBot-22 introduces the largest graph-based Twitter bot benchmark with high-quality annotations and evaluates 35 baselines across nine datasets.

Shangbin Feng, Zhaoxuan Tan, Herun Wan, Ningnan Wang and 18 more

Published Jun 9, 2022 · 46 citations · Code ★ 270

PAR: Political Actor Representation Learning with Social Context and Expert Knowledge

PAR learns political actor representations by integrating social context and expert knowledge into a unified framework.

Shangbin Feng, Zhaoxuan Tan, Zilong Chen, Ningnan Wang and 4 more

Published 2022 · 8 citations

Rubato: Transcribing Piano Music with Timestamps

Nazif Tamer, Victoria Ebert, Guang Yang, Noah Smith

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Toward Multimodal Sheet Music Recognition and Understanding

Guang Yang, Brian Zheng, Victoria Ebert, Noah Smith

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Why Copy Others? Insights into Social Learning from Multi-Agent Reinforcement Learning

Yancheng Liang, Shakti Senthil, Daphne Chen, Simon Du and 1 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

HearSayBench: Can LLMs Navigate from Abstract Human Rights to Lived Lives?

Sobhan Lotfi, Ava Iranmanesh, Ali Iranmanesh, Liwei Jiang

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

The Pok\'emon Theorem and other Fairness Impossibility Results

Daniel Matsui Smola, Alexander Smola

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Position: Reconciling Open Access with Owner Control in AI Model Distribution Deserves More Research Effort

Zerui Cheng, Edoardo Contente, Benjamin Finch, Oleg Golev and 7 more

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Time series analysis with Gumbel dynamics

Yiliu Wang, Timothy Kim, Eric Todd SheaBrown, Uygar Sümbül

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Ordinal Geometry Complements Reconstruction: Diagnosing Planning with Compressed Value Functions

Shiheng Zhang

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

MvFFN: Multi-view Floor-Plan Feed-Forward Network for Unposed Wide-Baseline Panorama Layout Reconstruction

Yuguang Li, Yichuan (Ethan) Deng, Zixuan Liu, Ivaylo Boyadzhiev and 4 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Multi-Turn RL Makes Small Language Model Competitive for Optimization Modeling

Xinzhi Zhang, Zeyi Chen, Humishka Zope, Hugo Barbalho and 5 more

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Embedded-Arena: Building Hardware-in-the-Loop Coding Agents to Run AI on Microcontrollers

Zhihan Zhang, Alexander Le Metzger, Jiuyang Lyu, Chun-Cheng Chang and 9 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Margin Dynamics for Large Language Model Alignment

Xingzi Xu, Saygin Seyfioglu, Karim Bouyarmane

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

When Should Agents Remember? Falsification-Gated Self-Evolution for LLM Agents

Runxuan Tang, Haoyu Gao, Yuyan Ding, Junyi Yao and 3 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Can We Trust Item Response Theory for AI Evaluation?

Han Jiang, Sunbeom Kwon, Jinwen Luo, Ziang Xiao and 1 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Rethinking Visual Reasoning in Text-to-Image Reward Modeling

Shiye Su, Xiaohan Wang, Ludwig Schmidt, Serena Yeung-Levy

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Neural Refraction Fields for Image Verification

Sage Simhon, Jingwei Ma, Prafull Sharma, Lucy Chai and 2 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

SMI: Semantic Medical ID for Hierarchy-Aware Concept Representation

Ziyang Song, Lia Shen, Yixuan Li, Qincheng Lu and 5 more

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026

M*: A Modular, Extensible, Serving System for Multimodal Models

Atindra Jha, Naomi Sagan, Keisuke Kamahori, Irmak Sivgin and 8 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Shellsort as Multi-Scale Relaxation: Learning Spectrum-Matched Gap Schedules

Qingyun Li, Ruoyun Li, Yunqi Li, Yunjin Li

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026

Tropical Gaussian Anticoncentration: Settling Optimal Instance-Dependent Bounds for Online Learning in Extensive-Form Games

Ashkan Soleymani, Zhiyuan Fan, Lillian Ratliff, Patrick Jaillet and 1 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

CFC26: Building Evaluations for Deployment in Sonar-Based Fish Counting

Madison Van Horn, Suzanne Stathatos, Sevan Brodjian, Justin Kay and 5 more

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

HiLoRA: Adaptive Hierarchical LoRA Routing for Training-Free Domain Generalization

Ziyi Han, Huanyu Wang, Zeyu Zhang, Xiangxiang Dai and 2 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Community-Centered AI is Feasible and Beneficial for Impacted Communities

Tzu-Sheng Kuo, Quan Ze Chen, Amy Zhang, Kenneth Holstein and 1 more

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Linear Contextual Bandits with Quasi-Optimism

Min-hwan Oh, Harin Lee

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Agentic Abstention: Do Agents Know When to Stop Instead of Act?

Han Luo, Bingbing Wen, Lucy Lu Wang

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

DUIL: Deep Unsupervised Inverse Learning for in situ Macromolecular Morphology Identification

Mostofa Rafid Uddin, Seonghui Min, Mahek Vora, Qifeng Wu and 2 more

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

JARVIS-Bench: Benchmarking Personal Intelligence Agents on Long-Horizon Real-User Daily Traces

Weizhi Zhang, Wei-Chieh Huang, Yueqing Liang, Liwei Jiang and 36 more

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Unifying Partner and Environment Diversity to Improve Human-AI Coordination

Patrick Q Zhang, Yancheng Liang, Adrienne Fairhall, Natasha Jaques

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Mitigating Overgeneralization in RND via Spectral Target Design

Minseok Jeong, Yechan Lee, Hyewon Choi, Jeongyong Yang and 1 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Ensemble Modeling for Time Series Forecasting: an Adaptive Robust Optimization Approach

Adaptive robust optimization builds time-varying linear ensembles of forecasting models that reduce error by 16, 26% and risk by 14, 28% versus best single members and competing methods.

Leonard Boussioux, Henry Mao, Dimitris Bertsimas

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

ABC-Align: Prediction-Powered Alignment with Adaptive Bias Control

ABC-Align minimizes variance via pseudo-labels and applies adaptive, lightweight bias correction tuned by plug-in estimates, outperforming semi-supervised alignment baselines with scarce human feedback.

Eric Frankel, Banghua Zhu, Sewoong Oh, Lillian Ratliff

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Adaptive Calibration in Non-Stationary Environments

Online prediction algorithms achieve calibration error adapting to non-stationarity via $\tilde O(\min\{\sqrt{T}+(TC)^{1/3},\sqrt{KT}\})$ bounds, smoothly interpolating between i.i.d. and adversarial settings.

Junyan Liu, Haipeng Luo, Lillian Ratliff

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

Online Bayesian Calibration under Gradual and Abrupt System Changes

BRPC enables online Bayesian calibration under nonstationarity by separating particle-based parameter updates from discrepancy updates, with restart mechanisms for abrupt regime shifts, improving accuracy over baselines.

Yang Xu, Chiwoo Park

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026

RefDecoder: Enhancing Visual Generation with Conditional Video Decoding

RefDecoder conditions video VAE decoders on reference images via attention to recover lost detail, boosting reconstruction PSNR by up to 2.1 dB and improving consistency across video generation tasks without retraining.

Xiang Fan, Yuheng Wang, Bohan Fang, Jason Ren and 1 more

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026

Factorized Spectral Representations for Reinforcement Learning

FaStR applies CP tensor decomposition to transition dynamics via contrastive learning, yielding separate state, action, and next-state encoders that shrink sample complexity and enable cross-actuator transfer.

Junyi Wu, Dan Li

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Membership Inference on Synthetic Single-Cell Genomic Data

Membership inference attacks successfully identify training donors in synthetic single-cell RNA-seq data, revealing that leading generation methods inadequately protect privacy and leak more as donor counts drop.

Steven Golob, Patrick McKeever, Sikha Pentyala, Martine De Cock and 1 more

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026

Global Convergence of Four-Layer Matrix Factorization under Random Initialization

Gradient descent globally converges for randomly initialized four-layer matrix factorization with balanced regularization, avoiding saddles in polynomial time.

Minrui Luo, Weihang Xu, Xiang Gao, Maryam Fazel and 1 more

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models

LEAD adaptively calibrates reasoning length via online self-adaptive rewards, achieving highest accuracy and efficiency scores with shorter outputs than base reasoning models.

Songtao Wei, Yi Li, Zhikai Li, Xu Hu and 6 more

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026 · ▲ 6 on Hugging Face · Code ★ 4

MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction

MolmoMotion predicts goal-conditioned 3D point trajectories from visual history and language, outperforming baselines on PointMotionBench and improving robot manipulation and video synthesis.

Jianing Zhang, Chenhao Zheng, Yajun Yang, Rustin Soraki and 6 more

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026 · ▲ 53 on Hugging Face · Code ★ 151

MedMisBench: Measuring Epistemic Resilience of LLMs Under Misleading Medical Context

MedMisBench reveals LLM medical accuracy collapses from 71% to 38% under misleading context, exposing a critical evaluation blind spot around epistemic resilience.

Hongjian Zhou, Xinyu Zou, Jinge Wu, Sean Wu and 18 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

SceneBind: Binding What and Where Across Vision, Audio, and Language

SceneBind binds vision, audio, and language via semantic-spatial entities and matching to achieve state-of-the-art cross-modal scene retrieval and spatial grounding.

Mingfei Chen, Zijun Cui, Ruoke Zhang, Hyeonggon Ryu and 1 more

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026