AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems

AgentGrad improves multi-agent prompt optimization via sequential intervention and semantic gradient clustering, achieving state-of-the-art performance with 2.5x faster optimization and 21.8% lower cost.

Jaewon Chu, jinwoo seo, Jaewon Cho, Jeehye Na and 3 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 107 on Hugging Face

PRISM: Principal Subspace Alignment for Parameter-Efficient Fine-Tuning

Anh Tong, Kyowoon Lee, Jaesik Choi

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

Refining Compositional Diffusion for Reliable Long-Horizon Planning

Kyowoon Lee, Yunhao Luo, Anh Tong, Jaesik Choi

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

GRASP: Learning to Ground Social Reasoning in Multi-Person Non-Verbal Interactions

Junho Kim, Xu Cao, Houze Yang, Bikram Boote and 5 more

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

ASAP: Attention Sink Anchored Pruning

Jaehyuk Lee, Hanyoung Kim, Yanggee Kim, Donghun Lee

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

Gauge-Symmetric Dual Lagrangian Frameworks for Born-Oppenheimer Molecular Dynamics

Sungwoo Park, Jongwon Lee, Jiwoong Kim, Hyung-sik Yoon

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

Semantic-Level Invariant Representation Learning for Cross-Hospital Clinical EEG Modeling

Kang Yin, Hye-Bin Shin, Seong-Whan Lee

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

SaMA: Morpho Adaptation via Asymmetric Expansion of Kronecker Product

An Nguyen, Anh Tong

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

Symplectic Parallel Scan: A Neural Hamiltonian Framework for Accelerated Scientific Simulation

Sungwoo Park

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

How Complete Should a Reference Be? A Benchmark Audit for Fluorescence Spot Detection

Jiyeong Kong, Pan-Gyun Jeong, Kyung-Tae Kang

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

Heads That Write, Not Just Point: Image Retrieval Heads in Vision-Language Models

Junsung Park, Uiwon Hwang, Donghun Kang, Yeongtak Oh and 5 more

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

MoEZip: Routing-Aware KV Cache Compression for Sparse Mixture-of-Experts LLMs

Minsang Kim, Seung Baek

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

Mitigating Knowledge Conflicts in Retrieval-Augmented Generation via Inference-Time Representation Editing

Dahyun Jung, Jaehyung Seo, Heuiseok Lim

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

Generation-Drift-Guided Block Pruning for Large Language Models

ZHIQI HUANG, Heedong Kim, ZHANG LINTONG, Seong-Whan Lee

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

HAPACT: A Benchmark For Human-Centric Physical Impact Localization in Movies

Youngrae Kim, Yejin Jang, Eunho Kim, Youjin Sung and 3 more

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

Safe Active Learning with Future Viability Guarantees in Time-Series Models

Hyeonjun Park, Whiyoung Jung, Deunsol Yoon, Sunghoon Hong and 2 more

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

MINT: Meeting-time INdicators for Truncation in Multi-Step Off-Policy RL

Seungyub Han, Taehyun Cho, Dohyeong Kim, Kyungjae Lee and 1 more

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

SIMBAD: Spatio-Temporal Traffic Forecasting Robust to Aperiodicity

Daniel Yoonhwan Lee, Seungwon Shin, Seunghoon Han, Sungsu Lim and 1 more

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

Merging RLVR-Trained Experts via Policy-Shift-Guided Spectral Alignment

Geeho Kim, MINSIK CHOI, Kyle Min, Young Geun Kim and 1 more

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

V-LUMEN: Visual Lookup Memory for Embedding Scaling in Vision-Language Models

Miso Choi, Daekeun Kim, Eunji Kim, Jungbeom Lee

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

Efficient Brain-to-Speech Decoding with Fixed-Delay Spiking Neural Networks

Aleksandra Wisniewska, Seo-Hyun Lee, Seong-Whan Lee

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

ProPolar: Progressive Polar Decomposition for Implicit Neural Representations

Pureum Kim, Younggeon Ryu, Dongyoon Lee, Hae Beom Lee and 1 more

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

Cortically-Resolved Recurrent Architecture for fMRI

Da-Woon Heo, Kwanseok Oh, Adrián Ayuso-Muñoz, Heung-Il Suk

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

Rethinking Attention in Depth for Operator Learning

Jaehyeon Lee, Kiwon Um, JungHyun Han, Min-Koo Kang

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

Meta Inverse Prompting for Video Generative Models

Yerin Jung, Jongheon Jeong

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

Constant Term Shrinkage for Federated Learning

Incheol Baek, Minseo Kim, Hyeonmin Kang, Yon Dohn Chung

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

ADMIT: Support-Gated Memory-Write Admission for Document QA Agents

Joongmin Shin, Gyuho Shim, Hyeonseok Moon, Jaehyung Seo

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

Fast Sandwich Products in Clifford Algebra

Travis Pence, Daisuke Yamada, Jiaqi Mo, Chanyoung Moon and 2 more

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

Spectral Unlearning: Transformer Structure-Preserving Updates for Language Model

Sung Il Choi, Junhao Cai, Dohun Kim, Changhee Joo

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

VideoMaMa++: Temporally Consistent Video Matting via Preserve-and-Refine Tokens

Sangbeom Lim, Seoung Wug Oh, Heeji Yoon, Seungryong Kim and 1 more

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

NPUsper: Eliminating Redundant Computation for Real-Time Whisper on Mobile NPUs

NPUsper eliminates redundant Whisper computation on mobile NPUs via online hallucination detection and chunked decoding to cut latency, TTFT, and power.

Hojeong Lee, Si H Lee, Sungwon Woo, Chengpo Yan and 2 more

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

FiRe: Fine-grained Multimodal Reasoning for Enhanced Image Generation

FiRe improves image generation via fine-grained multimodal reasoning that decomposes prompts, self-checks visual requirements, and applies localized refinement, with FiRe-GRPO providing step-level reinforcement learning rewards.

Yongjin Kim, Yoonjin Oh, Ye Rin Kim, Hyomin Kim 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 · Code ★ 2

Reason in the Words You Speak: Idiolectal Paraphrasing Off-Policy Traces for Reasoning Distillation in VideoLLMs

Echo-GRPO rewrites off-policy reasoning traces into a student VideoLLM's idiolect to avoid gradient clipping, improving reasoning distillation across backbones and benchmarks.

Ji Soo Lee, Jinyoung Park, Seohyun Lee, Jongha Kim and 3 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 24 on Hugging Face

TimeTok: Granularity-Controllable Time-Series Generation via Hierarchical Tokenization

TimeTok introduces hierarchical tokenization for multiscale time-series generation with explicit granularity control from coarse inputs, achieving state-of-the-art results and cross-dataset transfer.

Seokhyun Lee, Jaeho Kim, Changjun Oh, Mihaela van der Schaar 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

Stitched Value Model for Diffusion Alignment

StitchVM stitches pretrained pixel-space reward models onto frozen diffusion backbones to build accurate noisy-latent value functions for efficient diffusion alignment, accelerating DPS 3.2× and DiffusionNFT 2.3×.

Hyojun Go, Hyungjin Chung, Prune Truong, Goutam Bhat and 7 more

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

MVVBench: Benchmarking 4D Reasoning in Vision-Language Models

MVVBench benchmarks 4D multi-view video reasoning requiring joint cross-view temporal integration, finding vision-language models fail due to temporal mis-localization and cross-view identity breaks, with inference-time scaffolding and reinforcement learning yielding substantial gains.

Hyungjin Chung, Byeongjun Park, Joonseok Lee, Hojun Kim and 2 more

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

Overcoming Kernel Redundancy for Scaling Logic Gate Networks

Naive width scaling introduces redundant logic kernels that saturate performance, but dynamic kernel routing via gate-level Boolean operations restores scaling benefits and improves accuracy with better parameter efficiency.

Sejin Park, Hongjae Lee, Changwoo Han, Seung-Won Jung

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

Exact Posterior Score Estimation for Solving Linear Inverse Problems

Exact posterior score estimation derives closed-form posterior scores for linear Gaussian inverse problems, enabling efficient training and sampling that outperforms baselines with far fewer evaluations.

Abbas Mammadov, Ozgur Kara, Kaan Oktay, Iskander Azangulov and 4 more

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

AgentHop: A Diagnostic Benchmark for Agentic Multi-Hop Scientific Question Answering

AgentHop diagnoses agent failures via multi-hop scientific QA under constraints, finding model-family tool-use fingerprints and hidden within-family differences.

Chanhee Park, Jeongho Yoon, Sungbin Han, Hyeonseok Moon and 1 more

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

Consistency-Preserving Concept Erasure via Unsafe–Safe Pairing and Directional Fisher-weighted Adaptation

PAIR reframes diffusion model concept erasure via unsafe-safe pairs, using paired semantic realignment and directional Fisher-weighted adaptation to remove targeted concepts while preserving structural and semantic consistency.

Yongwoo Kim, Sungmin Cha, Hyunsoo Kim, Jaewon Lee and 1 more

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

Uniform Stability and Generalization Error of GD and SGD on Fixed-Point Parameters

Fixed-point GD degrades generalization to O(T/√n) with vacuous stability, while SGD yields tight O(T/n) or O(T²/n) stability and rounding can add dimension-dependent error.

Jonghyun Shin, Sejun Park

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

COMET: Codebook-based Online-adaptive Multi-scale Embedding for Time-series Anomaly Detection

COMET uses multi-scale patch encoding, vector-quantized codebooks, and online adaptation to detect time-series anomalies, achieving best performance on 36 of 45 metrics.

JINWOO PARK, Hyeongwon Kang, Seung H Han, Pilsung Kang

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

Accelerating Video Inverse Problem Solvers with Autoregressive Diffusion Models

AVIS uses autoregressive diffusion for streaming video inverse problems, cutting latency from 114s to 4s and boosting throughput to 1.18 FPS with better quality, while AVIS Flash reaches 5.91 FPS.

Taesung Kwon, Jonghyun Park, Hyungjin Chung, Jong Chul Ye

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

Learning to Solve Generative ODEs Beyond the Linear Span

SpanLift augments scalar ODE solvers with a spatial residual operator to overcome span limitations, achieving state-of-the-art few-step generative sampling without extra model evaluations.

Sihyeon Kim, Seunghun Lee, Vikas Singh, Hyunwoo J. Kim

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

Retain-Neutral Surrogates for Min-Max Unlearning

ROSU constrains min-max unlearning to retain-orthogonal surrogate perturbations for closed-form updates and reduced retain damage in high-coupling regimes.

Junhao Cai, Dohun Kim, Dowon Kim, Sung Il Choi and 3 more

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

AETDICE: Unified Framework and Offline Optimization for Nonlinear Multi-Objective RL

AET framework unifies nonlinear multi-objective RL under SER and ESR via aggregation-expectation-transformation decomposition, and AETDICE enables offline optimization via augmented density-ratio estimation.

Woosung Kim, Youngjun Suh, Jinho Lee, Jongmin Lee and 1 more

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