LexReward: A Taxonomy-Driven Reward Framework for Legal Language Models

LexReward introduces taxonomy-driven rubric-based rewards for legal language models across style, element, and reasoning dimensions, improving DPO and reinforcement learning performance.

Yida Cai, Xin Dai, Bingxiang He, Huiyuan Xie and 4 more

Published Sep 30, 2026 · 0 citations · ▲ 51 on Hugging Face

Does Learning Protein Folding Generalize to Broader Reasoning?

Post-training on protein-folding data via discrete answers and continuous geometry improves structure prediction and broad reasoning across ten benchmarks.

Yong Liu, Zhanpeng Shi, Yizhou Dang, Zhongyue Zhang and 3 more

Published Sep 30, 2026 · 0 citations · ▲ 120 on Hugging Face · Code ★ 28

Not Every Image Teaches Vision: Visual-Necessity-Gated Continual Learning for Multimodal Large Language Models

Jiamu Xue, Haidong Kang, Wen Luo, Jubo Chen and 1 more

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

Beyond Linear Decoders: Dynamic Expert-Coupled Optimal Decoding for Time Series Forecasting

Binwu Wang, Zhipeng Liu, Zhengyang Zhou, Pengkun Wang and 1 more

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

RECIPE: Procedural Planning via Grounding in Instructional Video

Luigi Seminara, Antonino Furnari, Lorenzo Torresani

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

Two-Clustering Regime of Token Dynamics in Causal Attention

Trinh Nguyen, Duy-Tung Pham, Hoang-Son Do, Tan Nguyen and 1 more

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

DiM$^3$: Bridging Multilingual and Multimodal Models via Direction- and Magnitude-Aware Merging

Zijing Wang, Mingyang Wang, Ercong Nie, Yongkang Liu and 5 more

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

Complementary Cache Guidance with Gradient Disentanglement for Continuous Test-Time Adaptation

Fanchun Meng, Yuhang Pei, Jiazhen Huang, Tao Ren and 3 more

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

UMAS: System-Level Uncertainty Quantification for Multi-Agent LLM Systems

Hanwen Li, Jinhao Duan, Xiaoshuang Shi, Yue Zhang and 3 more

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

Qubrio: High-Performance Quantum Compilation via Multi-Agent LLM Collaboration

Jixuan Ruan, Zhuo Cui, Zhengding Hu, Zhongkai Yu and 9 more

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

AdShot: Benchmarking Multimodal Large Language Models for Video Advertisement Clipping

Wen Xie, Om Rastogi, Sai S Rangoju, Gijs Overgoor and 2 more

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

Markovian Experimental Design under Concept Drift

Ayberk Yarkin Yildiz, Lili Su, Carlee Joe-Wong, Edmund Yeh and 1 more

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

Contextualized Evaluation of Vision Language Models through Dynamic Interviews

Yijiang Li, Huiqi Zou, Bingyang Wang, Ziang Xiao

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

The Power of a Random Sample in Online Algorithms

Omer Wasim, Sami Davies, Shallu Tomer, Rathish Das

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

First-Token Attraction in Mamba Dynamics

Trinh Nguyen, Duy-Tung Pham, Minh-Khoi Nguyen-Nhat, Hoang-Son Do and 2 more

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

PLACE: Patch-Level Agnostic Concept Extraction

Gabriele Onorato, Fabrizio Silvestri, Nathaniel D Bastian, Francesco Restuccia

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

PATH: A Dual Perspective for High-quality Text-attributed Graph Learning

Yuhang Pei, Fanchun Meng, Changhu Wang, Tao Ren and 5 more

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

CLEAR: Complementary Tripartite Play with Bayesian Calibration for Semi-Supervised Edge Classification

Zhipeng Sun, Fanchun Meng, Jiazhen Huang, Yongpeng Zhang and 4 more

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

Reward Shaping to Improve Language Model Query Generation

Shicheng Liu, Zeyu Zhang, LEI LU, Kexuan Sun and 1 more

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

METAFORGET: Audit-Driven Update-Policy Learning for Reliable Language Model Unlearning

Pinlong Zhao, Xiaoling Zhou, Zhou Zhaoting, Guangyuan Dong

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

LDPCache: Locally Differentially Private Multi-Query Processing with Cache Optimization for Large Language Models

Haoqiang Shi, Ning Wang, Chuan He, Qian Ma and 4 more

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

Shepherd: A Runtime Substrate Empowering Meta-Agents with a Formalized Execution Trace

Simon Yu, Derek Chong, Ananjan Nandi, Dilara Soylu and 3 more

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

What Transformer FFNs Never See: Theory, Diagnosis, and Lightweight Remediation

Tinghe Zhang, Yucheng Xiao, Alex Lamb

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

Stability in Multi-Step Reasoning via Jacobian-based Error Accumulation Analysis

Dongyue Li, Alice Duan, Ziniu Zhang, Hongyang Zhang

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

Generalizing Action-Conditioned Latent World Models with Video Model Rewards

Haichao Zhang, Yijiang Li, Shwai He, Van T Le and 2 more

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

Weird Generalization from Narrow Finetuning: Persona Shifts and Inductive Backdoors

Jan Betley, Jorio Cocola, Dylan Feng, James Chua and 3 more

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

RECAP: Looking Once Is Not Enough for Vision-Language Reasoning

Zhaolu Kang, Tailong Luo, Chenxin Li, Zhenyu Yu and 12 more

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

OTel: Open Telco AI Datasets, Benchmarks, and Models

Farbod Tavakkoli, Gregory Diamos, Kenneth Church, David Kanter and 14 more

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

Decompose the Distillation: Interpretable Single-Pass Guidance for Diffusion Models

Wuyang Zhang, Xiaolin Xu

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

Benchmarking Risk Attitudes of LLMs

Bowen Sun, Rui Min, Xianyao Li, Yuxi Wang and 3 more

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

Designing Kernel Surrogate Models for Multimodal Attribution

Ziniu Zhang, Zhenshuo Zhang, Jianglin Lu, Ruoxuan Xiong and 2 more

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

Rethinking in Spikes: Mitigating Hallucinations in MDLMs with Step-Aware Decoding

Zhongxing Xu, Zhonghua Wang, Zhe Qian, Shiyan Su and 8 more

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

We Need to Improve Benchmarks in AI for Mathematics

Simon Frieder, Jonas Bayer, Shi Zhuo Looi, Jacob Loader and 14 more

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026

Position: LLM Privacy Requires a Lifecycle-Wide Approach

Niloofar Mireshghallah, Tianshi Li

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

Claims of AI emergence should be grounded in information decomposition

Christoph Riedl, Fernando Rosas

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026

Memory is Not Search: Towards Proactive, Lifelong Memory in AI

Will Xiao, Sanket Deshpande, Guha Mahesh, Spandan Madan and 1 more

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

Human–AI Collaboration Requires a High-Order Dynamic Abstraction Substrate

Hengyu Liu, Dongxu Huang, Zhihong Cui, Lun Du and 4 more

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

FlashMask-3: Efficient and Expressive Mask-Aware Distributed Attention

Guoxia Wang, Qianyue He, Siming Wu, Haoyang Xie and 5 more

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

DnNP: Denoising Input Uncertainty in Neural Processes

Fatemeh Tohidian, Chengzhi Shi, Soomi Lee, Matthew Elia and 3 more

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

Optimal Byzantine-resilient Federated Learning with User-level Differential Privacy

Ming Xiang, Stratis Ioannidis, Edmund Yeh, Carlee Joe-Wong and 1 more

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

When Uncertainty Is the Target: Adversarial Attacks on Uncertainty-Aware Predictors

A Q M Sazzad Sayyed, Michele Caprio, Nathaniel D Bastian, Francesco Restuccia

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

RefineTok: Scale-Wise Tokenization for Progressive Visual Refinement

Yitian Zhang, Long Mai, Yizhou Wang, Yun Fu

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

DrugSAGE: Self-evolving Agent Experience for Efficient State-of-the-Art Drug Discovery

Yikun Zhang, Xiwei Cheng, Tianyu Liu, Yuanqi Du and 1 more

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

Firefly: Illuminating Verified Real-world Tool Call Data Generation

Yuxuan Lu, Ziyi Wang, Yingzhou Lu, Yisi Sang and 11 more

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

Referring and Reasoning Camouflaged Object Segmentation in Audio-Visual Scenes

Tianxin Han, Qing Dong, Xingwei Wang, Jie Jia

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026

Strong Post-Training from Permissive, Reasoning-Dominant, Web-Scale Pretraining

Harsh Raj, Ali Elganzory, Marianna Nezhurina, Victor May and 4 more

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

ContinuLoc: Continuous Pose Inference over Neural Fields for UAV Geo-Localization

Weikun Zhou, Jinliang Lin, Yu Zang, Lin Xie and 5 more

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

What are Key Factors for Updates in RL for LLM Reasoning?

Peidong Wang, Demi Wang, Xufang Luo, Jiahang Xu and 4 more

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026

Persona Vectors: Monitoring and Controlling Character Traits in Language Models

Runjin Chen, Andy Arditi, Henry Sleight, Owain Evans and 1 more

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

MaskSense: Confronting the Visual Exploration Trap in Masked Image Generation

Yawen Shao, Jie Xiao, Kai Zhu, Yu Liu and 5 more

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

Two Stages of Folding: Convergent Mechanisms in AI Protein Folding Trunks

Protein folding models share a two-stage trunk mechanism initializing biochemical signals then spatial features, with causally steerable, interchangeable representations across architectures.

Kevin Lu, Jannik Brinkmann, Stefan T Huber, Aaron Mueller and 3 more

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

How to Interpret Agent Behavior

ACT*ONOMY introduces a three-level taxonomy of 10 actions and 46 subactions for describing autonomous agent behavior at runtime, plus an open repository and automated analysis pipeline that compares behavioral profiles and surfaces failure patterns.

Sophia Gao, Kaiser Sun, Jen-Tse Huang, Katherine Van Koevering and 7 more

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

PhotoFlow: Agentic 3D Virtual Photography Missions

PhotoFlow uses a Director-Reviewer-Reflector agent for closed-loop camera search to generate language-conditioned virtual photographs in arbitrary 3D scenes, outperforming baselines on quality, alignment, and success rate.

Jiarui Guo, Haojia Wei, Yiming Zhang, Yifei Liu and 4 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 24 on Hugging Face · Code ★ 43

Consistent Geometric Deep Learning via Hilbert Bundles and Cellular Sheaves

A Hilbert bundle convolutional framework defines HilbNets for infinite-dimensional manifold signals, proving discrete versions converge to continuous architectures and transfer across samplings.

Kartik Tandon, Julian J Gould, Tanishq Bhatia, Francesca Dominici and 2 more

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026

MyoChallenge 2025: A New Benchmark for Human Athletic Intelligence

MyoChallenge 2025 benchmarks musculoskeletal sports control via simulated table tennis and soccer tasks, advancing agile motor algorithms across 70 teams.

Cheryl Wang, Chun Kwang Tan, Balint Hodossy, Shirui Lyu and 20 more

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

Geometric Signatures of Reasoning: A Spectral Perspective on Task Hardness

Reasoning trajectories are discrete hidden-state curves whose spectral flatness measures task hardness and whose kinematics predict correctness early.

Aria Masoomi, Mahsa Bazzaz, Adel Javanmard, Vahab Mirrokni

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

OmniMem: Scalable and Adaptive Memory Retrieval for Long Video Generation

OmniMem enables scalable long-video generation via sparse full-range KV retrieval with adaptive window exclusion and query-shared per-head scattered access, improving dynamic degree by 52.3% while preserving consistency.

Lin Zhao, Yushu Wu, Yifan Gong, Yanzhi Wang and 1 more

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

NS-VLA: Towards Neuro-Symbolic Vision-Language-Action Models

NS-VLA introduces neuro-symbolic encoding and hierarchical optimization to improve robotic manipulation generalization and exploration over prior VLA methods.

Ziyue Zhu, Shangyang Wu, Shuai Zhao, Zhao ZhiQiu and 7 more

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

How You Move Tells What You'll Do: Trajectory-Conditioned Egocentric Prediction

TrajPilot predicts future camera trajectories from egocentric video to condition action prediction, outperforming language-conditioned planners on procedural planning and anticipation.

SeJoon Jun, Hai Nguyen-Truong, Luigi Seminara, Lorenzo Torresani

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

Temporal Backtracking Search for Test-time Generative Video Reasoning

Temporal Backtracking Search improves video reasoning by searching over the temporal axis and restarting from verified prefixes rather than resampling from scratch, achieving 22.7% versus 0.7% best-of-N out-of-distribution.

SeJoon Jun, Zheng Ding, Huangyuan Su, Weirui Ye and 1 more

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

VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon

VLA-Corrector detects visual deviation via a lightweight monitor and triggers online replanning to adaptively correct action chunks without retraining VLA backbones.

Yi Pan, Miao Pan, Qi Lu, Jiaming Huang and 7 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 28 on Hugging Face · Code ★ 94

Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning

MAVIC corrects Bellman backups at instruction boundaries to maintain consistent value estimates under stochastic instruction switching, achieving high compliance with preserved cooperative task performance.

Wo Wei Lin, Ethan Rathbun, Enrico Marchesini, Xiang Zhi Tan

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

ReFPO: Reflow Regularization for Flow Matching Policy Gradients

ReFPO adds explicit reflow regularization to flow matching policy gradients, stabilizing training and enabling high-fidelity one-step inference that matches multi-step performance across control tasks.

Ge Wang, Yibo Peng, Fan Feng, Shenhao Yan and 9 more

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

SMoA: Spectrum Modulation Adapter for Parameter-Efficient Fine-Tuning

SMoA modulates spectra via block-diagonal Hadamard low-rank branches to expand representational coverage under small parameter budgets, outperforming LoRA on multiple tasks.

Yongkang Liu, Xing Li, Mengjie Zhao, Shanru Zhang and 6 more

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

Motion-o: Trajectory-Grounded Video Reasoning

Motion-o introduces trajectory-grounded video reasoning via explicit motion chains of thought, improving trajectory-faithful reasoning across benchmarks without architectural changes.

Bishoy Galoaa, Shayda Moezzi, Xiangyu Bai, Sarah Ostadabbas

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026 · ▲ 2 on Hugging Face · Code ★ 8

Structure Over Scale: Learning Visual Reasoning from Pedagogical Video

SoSVQA extracts 10K pedagogically structured QA pairs from children's video to train VLMs via GRPO, yielding major reasoning gains on NExT-QA, Video-MME, and MotionBench that match proprietary systems despite far less training data.

Bishoy Galoaa, Xiangyu Bai, Sarah Ostadabbas

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026 · ▲ 1 on Hugging Face

Embedding Foundation Model Predictions in Discrete-Choice Models with Structural Guarantees

A two-stage adapter embeds foundation model predictions into a constrained multinomial logit, guaranteeing cost monotonicity and valid value-of-time estimates while improving choice accuracy by up to 12.8 percentage points.

Yingshuo Wang, Xian Sun, Yanhang Li, Zhichao Fan and 1 more

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

Optimal Recalibration of an Online Predictor

An online algorithm achieves optimal ε-recalibration with ε² excess error in ε⁻³ rounds via Blackwell approachability, and yields simultaneous calibration and calibeating for smooth losses.

Lunjia Hu, Kevin Tian, Chutong Yang

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

Rethinking Ratio-Based Trust Regions for Policy Optimization in Multi-Agent Reinforcement Learning

MARS replaces ratio-based trust regions with a multiplicatively symmetric geometric barrier to cut variance and prevent probability collapse in multi-agent policy optimization. Across 47 tasks it matches or exceeds MAPPO and MASPO, with gains from barrier geometry rather than flexible boundaries.

Chulabhaya Wijesundara, Andrea Baisero, Zhongheng Li, Gregory D Castanon and 2 more

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

Truthful Calibration Errors for Multi-Class Prediction

The paper defines truthful multiclass calibration errors for linear label properties, proves they preserve Blackwell informativeness ordering, and show they stabilize model rankings across bin choices.

Yuxuan Lu, Yifan Wu, Jason Hartline, Lunjia Hu

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

SPANUQ: Span-Level Uncertainty Quantification for Large Language Model Generation

SPANUQ is a lightweight probe that estimates span-level LLM generation uncertainty via hidden-state distillation, outperforming sampling methods with 10, 20x speedups and 0.910 F1 span detection.

Yimeng Zhang, Yingying Zhuang, Ziyi Wang, Yuxuan Lu and 11 more

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

Consistency as a Testable Property: Statistical Methods to Evaluate AI Agent Reliability

The paper proposes statistical consistency metrics for AI agents that reveal strategy breakdowns hidden by standard pass rates, isolating architectural reliability flaws.

Harsh Raj, Niranjan Orkat, Suvrorup Mukherjee, Aritra Guha and 2 more

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

Drift Flow Matching

Drift Flow Matching bridges one-step drift models and iterative flow matching to enable adaptive sampling computation for flexible generation quality and efficiency.

Chenrui Ma, Xi Xiao, Lin Zhao, Tianyang Wang and 2 more

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

Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs

Palette enables modular, efficient relaxation of LLM refusal behaviors for authorized domains via lightweight adaptation and parameter merging while preserving general safety.

Qitao Tan, Xiaoying Song, Arman Akbari, Arash Akbari and 6 more

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

ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models

ActQuant uses action-guided mixed-precision quantization to compress vision-language-action models below 4 bits, retaining 95% task performance at 3 bpw and enabling edge deployment via native C/C++ kernels.

Arash Akbari, Arman Akbari, Masih Eskandar, Qitao Tan and 10 more

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026 · ▲ 2 on Hugging Face · Code ★ 19

A Multimodal Benchmark for Evaluating Cause-of-Death Inference Using Child Health and Mortality Data

This paper introduces a multimodal benchmark for cause-of-death inference in child mortality data, showing zero-shot language models synthesize unstructured medical evidence differently than supervised baselines.

Junhe Yang, Soumyakanti Pan, Hyun Seung Lim, YUE CHU and 17 more

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

ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model

ThinkJEPA combines dense JEPA dynamics with sparse VLM reasoning via dual pathways to improve long-horizon latent world modeling and trajectory prediction.

Haichao Zhang, Yijiang Li, Shwai He, Tushar Nagarajan and 4 more

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026 · ▲ 21 on Hugging Face · Code ★ 58

ChunkFT: Byte-Streamed Optimization for Memory-Efficient Full Fine-Tuning

ChunkFT enables memory-efficient full-parameter fine-tuning via dynamically activated sub-tensors, cutting 7B model memory to 13.72GB and outperforming baselines.

Yongkang Liu, Zijing Wang, Mengjie Zhao, Ercong Nie and 6 more

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

TRACER: Token ReAssignment for Concept ERasure in Generative Recommendation

TRACER reassigns semantic item tokens to erase target concepts in generative recommendation while better preserving recommendation utility than baseline unlearning methods.

Ziheng Chen, Jiali Cheng, Zezhong Fan, Diyuan Wu and 3 more

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

KV-PRM: Efficient Process Reward Modeling via KV-Cache Transfer for Multi-Agent Test-Time Scaling

KV-PRM eliminates text re-encoding by scoring via pre-existing KV caches, reducing process reward modeling cost from quadratic to linear and cutting latency and FLOPs by orders of magnitude.

Peng Kuang, Haibo Jin, Xiaoyu Han, Yanli Wang and 4 more

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

StaRPO: Stability-Augmented Reinforcement Policy Optimization

StaRPO improves reasoning via stability-augmented RL using autocorrelation and path-efficiency rewards, boosting accuracy and logical consistency.

Jinghan Zhang, Fengran Mo, Tharindu Cyril Weerasooriya, Ruimin Dai and 4 more

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

Post-Selection Distributional Model Evaluation

PS-DME enables statistically valid post-selection distributional model evaluation via e-values controlling false coverage rates, improving sample efficiency over sample splitting.

Amirmohammad Farzaneh, Osvaldo Simeone

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