STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning

STReasoner uses spatial-aware reinforcement learning to empower LLMs for spatio-temporal reasoning in time series, with large accuracy gains over proprietary models at low cost.

Juntong Ni, Shiyu Wang, Qi He, Ming Jin and 1 more

Published 2026 · 1 citation

Harder the Task, Sparser the Representation: Sparsity as a Learning Signature of Capability in LLMs

Mingyu Jin, Yutong Yin, Jingcheng Niu, Qingcheng Zeng and 7 more

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

CONSTRAINER: Promptable Graph-Structured Optimization via Constraint Conditioning

Zeeshan Memon, Mingke Tian, Xinyuan Song, Hongwei Jin and 2 more

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

FETTUCCINE: Fast and efficient brain-to-text decoding on mobile devices

Jonathan McCart, Pranav Deevi, Mehdi Azabou, Nanda H Krishna and 4 more

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

Cylindrical Geodesic Flow Matching for Quasiperiodic Physiological Signal Transformation

Onur Selim Kilic, Afra Nawar, Cem O Yaldiz, Michael J Cho and 5 more

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

Provably Efficient Representation Learning for Low-Rank CMDPs

Kaixuan Liu, GUOJUN XIONG, Shengpu Tang, Wanyun Si and 1 more

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

MixRoute: Rethinking Single-Distribution Training for Generalizable Neural Routing

Hang Yi, Ziwei Huang, Yining Ma, Zhiguang Cao

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

Autoregressive Diffusion World Models for Off-Policy Evaluation of LLM Agents

ADWM estimates LLM agent performance offline via a latent diffusion world model that alternates step-by-step with the policy, avoiding online interaction errors.

Kaixuan Liu, GUOJUN XIONG, Weinan Zhang, Shengpu Tang

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

PG-LRF: Physiology-Guided Latent Rectified Flow for Electro-Hemodynamic PPG-to-ECG Generation

PG-LRF uses a physiology-guided latent rectified flow with an electro-hemodynamic simulator to generate physiologically plausible ECGs from PPG, improving generation and cardiovascular disease classification.

Xiaoda Wang, Minxiao Wang, Kaiqiao Han, Defu Cao and 9 more

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

In-Context Optimization for Retrieval-Augmented Generation: A Gradient-Descent Perspective

Retrieval-augmented generation is framed as in-context optimization via linear self-attention gradient descent, yielding a frozen-model forward-only interface update that improves QA with low per-query cost.

mingchen li, Jiatan Huang, Chuxu Zhang, Liang Zhao and 1 more

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

Contrast encodes inductive bias: separating slow noise from dynamics in predictive representation learning

Contrastive predictive objectives that sample negatives across trajectories confuse slowly varying noise with true dynamics, but intra-trajectory negative sampling removes this shortcut and improves learned dynamics representations.

Paarth Gulati, Ilya Nemenman

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

Controllable Generative Sandbox for Causal Inference

CausalMix couples mixture Gaussian latent priors with type-specific decoders to generate realistic mixed-type tabular data with explicit, independent control over overlap, confounding, and treatment effect heterogeneity.

Qi Zhang, Harsh Parikh, Ashley I Naimi, Razieh Nabi and 2 more

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

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

SnapAudit: Active Auditing of Differentially Private In-Context Learning via Snapshot-Based Simulation

SnapAudit decomposes DP-ICL into deterministic and noisy stages and uses snapshot simulation to audit privacy 80-200x faster, revealing flaws in existing Gaussian calibrations and embedding sensitivity analyses.

Yuyang Xia, Ruixuan Liu, Li Xiong

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

PolyTopoBench: A Benchmark for Complex Vector Polygon Generation from Remote Sensing Imagery

PolyTopoBench benchmarks vector polygon generation from remote sensing images, finding existing methods fail on complex multi-ring topologies with holes.

Zeping Liu, Ni Lao, Weiwei Sun, Gil Wolff and 4 more

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

Multi-agent Collaboration with State Management

STORM mediates multi-agent shared workspace edits to detect and resolve conflicts at write time, outperforming isolated worktree baselines on Commit0 and PaperBench.

Mengyang Liu, Taozhi Chen, Zhenhua Xu, Xue Jiang and 1 more

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