Co-Evolving Policy Distillation

Co-Evolving Policy Distillation co-trains experts via bidirectional online policy distillation during RLVR to avoid divergence and absorption gaps, integrating multi-modal reasoning to surpass domain-specific experts.

Naibin Gu, Chenxu Yang, Qingyi Si, Chuanyu Qin and 6 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 67 on Hugging Face

MMTA: Benchmarking Multimodal Temporal Analysis with Time Series, Text, and Vision

Ziyang Zhang, Shenyi Li, Yilin wang, Ziyun Cui and 3 more

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

GenRM-Flow: Generators are Process-aware Reward Models in Flow Matching

Siming Fu, Zheming Fu, Ruizhe He, Zeyue Xue and 6 more

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

FrequencyBooster: Advancing Pixel Diffusion for High-Fidelity Image Generation

Lichen Ma, Zipeng Guo, Yu He, Xiaolong Fu and 4 more

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

GMO-E²DIT: Grounded Multi-Operation Editing for E-Commerce Images

Zipeng Guo, Xiaoan Liu, Lichen Ma, Cheng Wang and 8 more

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

Zero-Shot Coordination among LLM Agents

Adrian Hayler, Shashank Reddy Chirra, Andrei Lupu, Johannes Forkel and 3 more

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

CRAFT: Counterfactual-to-Interactive Reinforcement Fine-Tuning for Driving Policies

CRAFT combines dense counterfactual advantages with grounded residual corrections to reduce variance and bias in closed-loop autonomous driving fine-tuning, achieving strong Bench2Drive gains.

Keyu Chen, Nanfei Ye, Yida Wang, Wenchao Sun and 3 more

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

MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization

MM-IssueLoc benchmarks multimodal repository-level issue localization using visual evidence across 652 instances, showing current systems achieve under 39% file accuracy and text-only scores do not transfer.

Shaoxiong Zhan, Shi Hu, Hai Lin, BoyuFeng and 6 more

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

AdaCodec: A Predictive Visual Code for Video MLLMs

AdaCodec uses predictive visual codes to send full reference frames only when unpredictable, cutting video MLLM tokens by 7x while improving long-video benchmark scores and reducing latency.

Haowen Hou, Zhen Huang, Zheming Liang, Qingyi Si and 7 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 7 on Hugging Face

From Patches to Trajectories: Privileged Process Supervision for Software-Engineering Agents

P2T uses reference patches as privileged supervision to curate shorter, grounded agent trajectories via bi-objective optimization, improving SWE-bench Pass@1 by up to 10.8 points with ~15% lower inference cost.

Murong Ma, Tianyu Chen, Yun Lin, Shuai Lu and 6 more

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

Self-Distilled RLVR

RLSD combines RLVR and self-distillation, using token-level policy differences for update magnitudes and environmental feedback for directions, improving convergence and stability.

Chenxu Yang, Chuanyu Qin, Qingyi Si, Minghui Chen and 6 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 145 on Hugging Face

Harnessing Streaming Video in the Wild

Streaming-Train-248K and Streaming Harness adapt VLMs to real-time video streams with proactive interaction, 12-hour memory, and sub-second latency.

Dingyu Yao, Shuhuan Gu, Qingyi Si, Junhao Zhou and 7 more

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

AOT-POT: Adaptive Operator Transformation for Large-Scale PDE Pre-training

AOT-POT adaptively transforms diverse PDE solution operators into simpler aligned forms via multi-stream aggregation and Sinkhorn mixing, achieving state-of-the-art pre-training accuracy with minimal parameters.

Qitan Lv, Hong Wang, Hao Zhongkai, Wen Wu and 4 more

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

The Hidden Power of Scaling Factor in LoRA Optimization

LoRA's scaling factor dominates optimization by amplifying task signals without increasing drift, outperforming learning rate adjustments. The optimal alpha follows a sublinear square-root law with rank, revealing insufficient scaling in existing heuristics. Proposed LoRA-alpha restores principled s

Zicheng Zhang, Haoran Li, Jiaxing Wang, Guoqiang Gong and 9 more

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026 · ▲ 12 on Hugging Face

Adam under Generalized Smoothness with Second-Moment-Type Stochastic Gradients

Adam converges with high probability on generalized-smooth objectives under only second-moment stochastic gradients, matching a sharp δ^{-1/2} confidence dependence and yielding expectation rates for p<1.

ruinan Jin, Difei Cheng, Ling Chen, Jun Luo and 2 more

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

RA-CFGCache: From Branch-Level Criteria to Guided-Risk Control under Classifier-Free Guidance

RA-CFGCache aligns caching risk with CFG branch errors and timestep propagation to improve diffusion model efficiency and fidelity.

Yiming Liu, Ben Wan, Hui Chen, Ao Wang and 4 more

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