EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery

EvoDuet co-evolves solutions and web queries via a retrieval gate to boost LLM discovery gains up to 82.3% across optimization tasks.

Young-Jun Lee, Jinheon Baek, Soyeong Jeong, Minki Kang and 4 more

Published Sep 30, 2026 · 0 citations · ▲ 109 on Hugging Face · Code ★ 4

EgoTools: Towards Tool-Centric Reasoning in Real-World Egocentric Videos

EgoTools introduces a dataset and benchmark for egocentric tool-use reasoning, showing current models struggle with visual grounding while training improves performance.

Shulin Tian, Junsu Kim, Shuai Liu, Hao Li and 16 more

Published Sep 30, 2026 · 0 citations · ▲ 67 on Hugging Face · Code ★ 9

SlimWise: Decoupling Expert Pruning Across Prefill and Decode for Efficient MoE Serving

SlimWise decouples MoE expert pruning across prefill and decode phases to boost serving throughput without sacrificing accuracy via direct KV cache reuse and selective distillation.

Gunho Park, Kyoungho Jeun, Juntaek Oh, Byeongjun Shin and 2 more

Published Sep 28, 2026 · 0 citations · ▲ 5 on Hugging Face

Beyond Uniform Detection: Adaptive Hallucination Detection for RAG Across Response Regimes

Jungwuk Park, Sejong Ryu, Jy-yong Sohn, Jaekyun Moon

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

HyperFlow: Gradient-Free Test-Time Adaptation for Cross-Domain Few-Shot Classification

Donggyun Kim, Chanwoo Kim, Seunghoon Hong

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

PhaseDance: Capturing Rhythm and Expressivity in Dance Modeling

Meongeun Kim, Taehui Lee, Soomin Park, Sung-Hee Lee

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

AdKnob: Ad Intensity Control and Labeling for LLM-Native Advertising

Woo Jae Kim, Seongho Keum, Joonsung Jeon, Suhyeon Ha and 2 more

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

SchedDiff: Diffusion-Based Priority Refinement for Job Shop Scheduling

Dong-Yoon Oh, Sang-Hyun Cho, Inguk Choi, Hyun-Jung Kim

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

Less is More: Compact-Token Masked Feature Learning for Skeleton Representation Learning

Jeonghyeok Do, Yun Chen, Geunhyuk Youk, Munchurl Kim

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

Logit-Conditioned Diffusion Decoding for Frozen Discrete-Token VLMs

Ji Woo Hong, Hee Suk Yoon, Gwanhyeong Koo, Eunseop Yoon and 4 more

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

Collaborative Reasoning Distillation via Cross-Feedback and Coherent Curation

Taehoon Kim, Seunggeun Cho, Dongsu Han

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

A Structured LLM Framework for Inorganic Material Synthesis Planning

Heewoong Noh, Gyoung S. Na, Namkyeong Lee, Chanyoung Park

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

scTrilemma: Balancing Identity, Invariance, and Reconstruction in Single-Cell Representation Learning

Yunhak Oh, Yoonho Lee, Junseok Lee, Namkyeong Lee and 8 more

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

Training-Free Active Test-Time Adaptation for Vision-Language Models

Jihwan Bang, Sumyeong Ahn, Hwanjun Song, Jae-Gil Lee

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026

Chasing Label Shifters: A Change-Aware Framework for Dynamic Graph Node Classification

Junghoon Kim, Seungyoon Choi, Hyunsung Kim, Chanyoung Park

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

SRA: Spatial Reasoning Adapter via Evolving Social Interaction Graphs for Trajectory Prediction

Jaewoo Jeong, Seonkyu Song, Hyeonwoo Park, Jegyeong Cho and 4 more

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

Triggering Generalist Reasoning via Predictive Uncertainty for Dual-System VLA

Hyemin Yang, Wooseong Jeong, Giwon Lee, Kuk-Jin Yoon

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

Rethinking Credit Assignment in Cooperative MARL via Interventional Reward Response

Chamjin Joo, Myounghoon Ha, Sang Wan Lee

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

MASTARS: Multi-Agent Sequential Trajectory Augmentation with Return-Conditioned Subgoals

Jiwon Jeon, Myungsik Cho, Woojun Kim, Seongmin Kim and 3 more

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

AGiR: Mitigating Gift Over-Reliance in Mixed-Motive Games

Woohyeon Byeon, Seongmin Kim, Jiwon Jeon, Woojun Kim and 1 more

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

Addressing Exogenous Variability in Cooperative Multi-Agent Reinforcement Learning

Seongmin Kim, Woohyeon Byeon, Jiwon Jeon, Seungyul Han and 1 more

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

Root-Selecting Fixed-Point Inversion for Rectified Flows via Trajectory Straightness

SelFix selects fixed-point solutions by trajectory straightness for rectified flow inversion, improving reconstruction and editing accuracy.

Semin Kim, Jihwan Yoon, Seunghoon Hong

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

Towards Error-Free EHRs: Reasoning-Intensive Consistency Verification Between Clinical Notes and Structured Tables in Electronic Health Records

EHR-ReasonCon introduces a reasoning-intensive benchmark for clinical note-table consistency verification, and EHR-Inspector achieves state-of-the-art results via LLM-based verification with table exploration.

Yeonsu Kwon, Jiho Kim, Junseong Choi, Paloma Rabaey and 9 more

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

AtomMOF: All-Atom Flow Matching for MOF-Adsorbate Structure Prediction

AtomMOF uses all-atom flow matching to predict MOF and adsorbate structures directly from 2D graphs, improving match rates and sampling efficiency.

Nayoung Kim, Honghui Kim, Sihyun Yu, Minkyu Kim and 2 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · Code ★ 19

Screening Lipid Nanoparticles through Structure-Ratio Alignment

STRATA predicts lipid nanoparticle transfection by aligning molecular structure and composition ratio representations to model component interactions. It improves accuracy and generalizes to unseen molecules and ratios.

Yoonho Lee, Yunhak Oh, Hoyoung Choi, Chanyoung Park

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

MotionGrounder: Grounded Multi-Object Motion Transfer via Diffusion Transformer

MotionGrounder enables multi-object motion transfer via a diffusion transformer with flow-based motion signals, object-caption alignment loss, and a new object grounding score. It outperforms baselines in multi-object controllable video generation.

Samuel Teodoro, Yun Chen, Agus Gunawan, Soo Ye Kim and 2 more

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

Flow Map Language Models: One-step Language Modeling via Continuous Denoising

Continuous flow language models outperform discrete diffusion in quality and speed, and distilling their unique flow map enables one-step generation surpassing eight-step discrete diffusion.

Chanhyuk Lee, Jaehoon Yoo, Manan Agarwal, Sheel Shah and 5 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 4 on Hugging Face · Code ★ 172

Multi-view Relational Distillation for Spatial Reasoning with Vision-Language Models

Multi-view relational distillation improves vision-language model spatial reasoning by distilling cross-view patch similarities rather than features, preserving language alignment with minimal overhead.

Kiet Nguyen, Hanbo Shim, Jinwoo Kim, Seunghoon Hong

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

ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time Scaling

ExComm detects cross-agent factual conflicts during exploration to correct errors via soft belief updates and trajectory diversification, improving test-time scaling by up to 5.7%.

Woomin Song, Beomjun Kim, Daewon Choi, Sai Muralidhar Jayanthi and 3 more

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

Bellman Residual Minimization for Control: Geometry, Stationarity, and Convergence

Bellman residual minimization for policy optimization achieves stable convergence with function approximation but lacks extensive study; foundational control results are established.

Donghwan Lee, Hyukjun Yang

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

PatchKV: Weight Space Compensation of KV Cache

PatchKV improves KV cache compression by computing a context-specific weight patch via ridge regression to align compressed and full-cache activations, preserving long-context accuracy without increasing per-query cost.

Chanryeol Lee, Chanhyuk Lee, Yeonwoo Choi, Donggyun Kim and 1 more

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

Retrieve What’s Missing: Coverage-Maximizing Retrieval for Consistent Long Video Generation

COVRAG uses depth-based coverage maps and residual-gain frame selection to improve long-horizon geometric consistency in autoregressive video generation with low latency.

Minseok Joo, Dogyun Park, Taehoon Lee, Kyujin Lee and 1 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 25 on Hugging Face

Grounding Driving VLA via Inverse Kinematics

Reformulating driving VLA as inverse kinematics with future visual prediction and diffusion-based decoding recovers visual grounding, letting a 0.5B model match 7B-8B planning performance.

Junsung Park, Hyunjung Shim

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

Atom-level Protein Representation Learning Improves Protein Structure Prediction

TriProRep pretrains structure-aware protein representations via joint amino-acid, backbone, and full-atom token recovery, improving homodimer co-folding, interaction prediction, and monomer structure prediction over sequence-only models.

Taewon Kim, Hyosoon Jang, Hyunjin Seo, Seonghwan Seo and 5 more

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

EHRNote-ChatQA: A Benchmark for Evidence-Grounded Multi-Turn Clinical Question Answering over Longitudinal Discharge Summaries

EHRNote-ChatQA introduces multi-turn clinical QA over longitudinal discharge summaries, showing LLMs struggle with evidence grounding and multi-turn error accumulation.

Jiyoun Kim, Muhan Yeo, Eunhye Jang, Jeewon Yang and 13 more

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

Preference-Guided Adaptation for Open-Vocabulary Semantic Segmentation via Prompt Disagreement

A preference-guided framework adapts open-vocabulary segmentation using prompt disagreement as binary supervision, yielding consistent benchmark gains without pixel-level masks.

Hyun-Kurl Jang, Jihun Kim, Kuk-Jin Yoon

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

KL for a KL: On-Policy Distillation with Control Variate Baseline

vOPD casts on-policy distillation as RL and stabilizes it via a closed-form per-token reverse KL baseline that reduces gradient variance without extra inference cost.

Minjae Oh, Sangjun Song, Gyubin Choi, Yunho Choi and 1 more

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

Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor’s Internal States

POISE predicts baselines from a model's internal states via a lightweight probe for stable, low-cost multi-domain RLVR without separate critics.

Yunho Choi, Jongwon Lim, woojin Ahn, Minjae Oh and 2 more

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

GeoCore-9B: Towards Geo-Aware Generative Foundation Models in Earth Observation

GeoCore-9B is a 9-billion-parameter diffusion model trained from scratch on global earth observation data that conditions generation on geospatial metadata and achieves state-of-the-art visual fidelity and geographic accuracy.

Jeonghyeok Do, Munchurl Kim

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

WebSpline: Structure-Informed Splines for Real-Time 3D Gaussians from Monocular Videos

WebSpline uses structure-informed splines and a structural proxy graph to reconstruct dynamic 3D scenes from monocular video with state-of-the-art quality and over 10x faster rendering than prior methods.

Jongmin Park, Jeonghwan Yun, Minh-Quan V Bui, Munchurl Kim

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