AI Model2026
Scans long documents rendered as compressed page-images, locates relevant pages, and selectively expands only those pages to full text for question answering; built on Qwen3.5-9B, supports 5x/10x/15x compression and is released under Apple’s research-only model license.
AI Video Papers2026
Wangbo Yu, Kunhao Liu +9Affiliation: Peking Universityhttps://drexubery.github.io/WorldCrafter, Affiliation: ARC Lab, Tencent IEG
Learns a camera-queryable implicit 3D-aware memory that compresses multi-view history into target-view tokens to enable long-horizon, camera-controllable video generation. Improves revisit consistency and camera-control accuracy and supports streaming exploration from a single image or text prompt.
Xiaoqiang Wang, Mengyang Xiong +2Affiliation: Département d’informatique et de recherche opérationnelle, Université de Montréal, Montréal, QC, Canada, Affiliation: Mila, Quebec AI Institute, Montréal, QC, Canada +1
Adds token-conditioned quantum residual branches to a frozen masked-diffusion language model: a lightweight hypernetwork emits continuous quantum-circuit coordinates per token, executes a shared sparse IQP-style circuit, and injects classically-expressible expectation readouts back into transformer blocks. Trains only the added branches, scaling to 16–64 qubits with analytic, linear-cost readouts.
Evaluates whether generative world models maintain consistent, controllable, and physically plausible simulated environments under exploration, interaction, and intervention. Introduces a six-level W1–W6 capability taxonomy across three tracks (video, spatial, embodied) with human A/B Arena and automated metrics to measure behavioral correctness.
Jiahao Lu, Minghao Yin +6The Hong Kong University of Science and Technology, ARC Lab, Tencent IEG +2
Compresses a geometry-foundation model’s multi-level features into a compact latent that decodes jointly to RGB, depth, cameras and point maps — enabling a conditional flow to generate 3D-consistent video and novel views with measurably improved coherence.
Stores speaker-labeled verbatim messages alongside derived person- and group-level states to improve attribution and long-term memory in multi-party dialogues. Proposes a dual-track memory and a speaker-conditioned Writer trained with SpeakerLevenshtein and GRPO; yields consistent gains on multiple dialogue memory benchmarks.
Jaihyun Lew, Mingi Jung +3Interdisciplinary Program in AI, Seoul National University, Department of Electrical and Computer Engineering, Seoul National University +1
Uses diffusion-model forking moments as a proxy for perceptual distance to automatically generate pointwise reference-grounded labels, enabling annotation-free training of reference-based image quality assessment metrics.
Shows that Transformer LLMs output a superposition of next-token distributions when token embeddings from distinct text streams are linearly combined, finds this property is architectural but weakened by pretraining, and demonstrates it can be restored by lightweight fine-tuning and disentangled at decode time.
AI Dataset2026
Provides imagined interaction segments generated by world models for RoboTwin2.0 tasks, stored as fixed-length HDF5 chunks (21 observation frames, 20 actions, rewards and episode flags). Useful for training and evaluating world-model-based policies; currently limited to the RoboTwin2.0 subdataset.
Shows that private post-training changes leave measurable "behavioral shadows" in task-unrelated single-word outputs and proposes Active Taskless Distillation (ATD) to transfer capabilities to a student using only those single-word teacher responses, without teacher logits or parameters.
Trains decoders and diffusion generators to be robust to random subsets of pretrained encoder layers by regularizing layer-fusion during training, narrowing the reconstruction–generation gap in representation autoencoders and improving ImageNet-256 PSNR and gFID.
Evaluates multimodal memory in large audio language models by testing four acoustic evidence types and four memory operations across multi-session spoken histories, stratified across 8K–64K token context budgets.