Multimodal

The paper reports Kling's experience that video generation quality is the projection of multimodal understanding across the data, conditioning, alignment, and evaluation chain.

FactEmbed decouples composed-query comprehension from embedding learning by training factorized MLLM latents with target imagination, factor-level matching, and attention distillation, then reranking with mean-pooled latents.

YANAMI introduces a 400K-dialogue multimodal dataset and a 400-dialogue benchmark for multiturn stateful interaction, where models must track, update, and visually realize evolving dialogue states.

VidUEU-Agent is an automated agent pipeline that converts raw videos into 100K multimodal instruction samples and improves understanding, editing, and unified benchmark scores after fine-tuning.

Mage-VL-Cowork is a 4B hybrid computer-use agent trained through a five-stage curriculum on 318,837 trajectories generated by evolved GUI and terminal harnesses and reusable workflows, reaching 66.0% on OSWorld-Verified with a 50-step budget.

PhotoGuider measures four photographic tokens with compact learned scorers to select 360° view directions, rank and refine crops, output camera parameters, and generate measurement-conditioned explanations.

Reviso is an agentic video captioning framework that learns a Context-Focus-Points observation plan and uses verification-guided SFT plus GRPO rewards to gather prioritized visual evidence with tools.

The paper argues that embedding research across modalities is converging on shared principles and proposes a roadmap from transformation and alignment to joint omnimodal embedding, graded by coverage, comparability, and compositionality.

The paper introduces ReGap-Bench, a paired benchmark that holds scene, question, and answer fixed while varying visual references, and finds that task-matched references improve multimodal reasoning by up to 25% while mismatched references give little benefit or hurt.

LARC performs reasoning in continuous latent space for unified multimodal models, using curriculum SFT and self-evolving RL to improve image generation and enable test-time scaling.

A-RSI uses training-log reward-variation and accuracy signals to decide when to replace a pool of programmatically generated multimodal tasks, and reports gains on an eleven-benchmark suite without external training examples or human answer labels.

LOWN uses a cheap TEXT-ONLY forward to certify the latest image-conditioned predictions and runs the image-conditioned FULL forward only when the certified prefix is too short, retaining 99.6% of LLaDA-V's score at 35.3% of decoding FLOPs.

Youtu-Parsing-Omni is a 5B omni-modal parser that uses one shared text-initialized encoder and one unified schema to convert documents, images, audio, and video into spatially and temporally grounded structured records, with state-of-the-art document parsing and leading open-weight omni-parsing results.

The paper proves for JEPAs that separately trained modalities with shared positive pairs learn the same representation up to a rotation, and shows empirically that good views align better and more efficiently than bad views or next-token prediction.

IntReal introduces a real-world interleaved dataset and a coarse-to-fine expert-model evaluation suite for multimodal interleaved generation.

AskStream introduces an ask action and a multi-turn benchmark with Ask-F1 and StreamHarness for evaluating when and what streaming video models should ask under video and user uncertainty.

Falcon is a single-pass causal audio-visual target speaker extractor paired with the RealSSA benchmark, achieving strong extraction quality with much lower parameter, computation, and latency costs than causal AV-TFGridNet.

PreView is a trained auxiliary preprocessor that supplies center-guided cropped and enlarged views plus candidate-specific visual and textual cues to a frozen GUI grounding model, improving accuracy without retraining that model.

HuGe trains humanoid generalist VLAs on over 2,000 hours of egocentric human and robot data through a three-stage pipeline, using SONIC motion-token actions and data adaptation to achieve state-of-the-art HumanoidArena results and improved real-world G1 pick-and-drop success.