X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding

While video streaming understanding has made significant strides, real-world applications, such as live sports broadcasting, autonomous driving, and multi-screen collaboration, inherently demand continuous, multi-stream interactions. However, existing benchmarks are confined to single-stream paradigms, leaving a critical gap in evaluating online, cross-stream reasoning. To bridge this, we introduce X-Stream, the first benchmark dedicated to multi-stream streaming understanding. Comprising 4,220 rigorously curated QA pairs across 932 videos, X-Stream evaluates 11 subtasks across multi-window, multi-view, and multi-device scenarios. Crucially, our dataset is constructed using a novel dual-verification pipeline that prevents over-reliance on a single stream. Furthermore, we pioneer the conceptualization of multi-modal large language models (MLLMs) as naive multiplexers, systematically evaluating their performance through the lens of Signal Multiplexing Theory. Our extensive online inference experiments reveal a stark reality: state-of-the-art MLLMs struggle significantly with concurrent streams, achieving only about 50% score and exhibiting poor proactive ability. Ultimately, X-Stream exposes the trade-off of current multiplexing schemes, providing both a practical evaluation protocol and empirical guidance for next-generation multi-stream agents.

UNISON: A Unified Sound Generation and Editing Framework via Deep LLM Fusion

We present UNISON, a latent diffusion framework that unifies speech generation, sound generation, and audio editing within a single model. A single model handles text-to-audio, text-to-speech, zero-shot speaker cloning, mixed speech-and-sound generation, scene-level audio editing, speech-in-scene editing, and timed temporal composition, all of which share a single set of weights. Our architecture features two core designs: (1) Layer-wise deep LLM fusion, which injects hidden states from uniformly sampled layers of a frozen MLLM into corresponding MM-DiT blocks via learned projections, providing depth-matched semantic conditioning that improves instruction following over single-layer baselines; and (2) a unified multi-task architecture where task identity is encoded solely by a channel-wise mask and source audio is provided through VAE-encoded channel concatenation. Training is stabilized by an online GPU-side multi-task data synthesis pipeline with task-homogeneous batching and a two-stage curriculum. With 621M--732M trainable parameters, UNISON achieves results competitive with or exceeding task-specialist models across evaluated domains, while being roughly $4\times$ smaller than comparable unified systems.

UI-KOBE: Knowledge-Oriented Behavior Exploration for Lightweight Graph-Guided GUI Agents

Recent advances in mobile GUI agents have shown strong potential for automating mobile tasks, but most effective systems still depend on large vision-language models for screenshot understanding and long-horizon planning. Small GUI agents that can be deployed directly on mobile devices are more attractive for practical use, offering lower inference cost and better protection of sensitive on-device information. However, due to limited model capacity, such lightweight agents remain unreliable when planning and executing GUI tasks end-to-end from screenshots alone. We propose Knowledge-Oriented Behavior Exploration (\textbf{UI-KOBE}), a framework that improves lightweight mobile GUI agents with reusable app-specific graph knowledge. UI-KOBE first autonomously explores a mobile application and constructs an app knowledge graph, where nodes represent distinct UI states and edges represent executable transitions. At runtime, a lightweight GUI agent uses the graph as external guidance: given a user task and the current screenshot, it identifies the current graph node and selects among self-loop actions, neighboring transitions, task completion, or fallback free actions associated with that node. By supporting runtime decisions with app-specific graph guidance, UI-KOBE reduces the burden of end-to-end GUI planning and helps lightweight models perform mobile GUI tasks more effectively, offering a practical step toward efficient, interpretable, and privacy-conscious on-device GUI agents.

OmniInteract: Benchmarking Real-World Streaming Interaction for Real-Time Omnimodal Assistants

We introduce OmniInteract, a streaming benchmark for real-time omnimodal large language models evaluated through native online inference over audio-visual streams. Unlike offline video understanding or text-prompted streaming QA, OmniInteract preserves the original audio-visual stream and requires models to process it online, without access to future content. User queries and ambient sounds are embedded in the audio track, requiring models to detect multimodal triggers, decide when to respond, and answer while the stream unfolds. OmniInteract contains 250 videos with 1,430 temporally grounded response slots: 1,062 1Q1A slots across real-time, proactive, and nested scenarios, and 368 1QnA slots for continuous task monitoring and step guidance. Each slot includes a trigger, response window, and target answer. We evaluate response correctness, timing, invalid outputs, interruption handling, and context continuity using Interaction-Aware Quality-Timeliness F1, Interruption Diagnostic Suite, and Nested Chain Completion Score. Experiments show that current models remain weak in streaming interaction, with the best overall IA-QTF1 reaching only 0.368 and the best 1QnA IA-QTF1 only 0.052. Further study on mathematical reasoning in full-duplex settings shows that offline capability does not necessarily transfer to online interaction. Code and datasets will be made publicly accessible at https://github.com/Lucky-Lance/OmniInteract.

Not All Tokens Matter Equally: Dynamic In-context Vector Distillation with Decisive-Token Supervision for Long-form Medical Report Generation

Distilling demonstration effects into hidden-space interventions offers a lightweight alternative to full finetuning. However, existing multimodal variants are mostly evaluated on short-form tasks, where outputs end after a few tokens. Extending these methods to long-form generation exposes a fundamental yet underexamined limitation: token-level distillation implicitly treats all output tokens as equally informative, but long-form outputs are dominated by high-frequency template and grammatical tokens, while the tokens that actually determine output quality are sparsely distributed. In medical report generation (MRG), two such decisive tokens stand out: pathology-related tokens that determine diagnostic content, and the end-of-sequence (EOS) event that determines termination. Both receive insufficient supervision under uniform cross-entropy, and autoregressive decoding further compounds the problem by drifting away from teacher-forced trajectories. We propose DIVE, a frozen-backbone distillation framework that addresses long-form report generation through two complementary mechanisms matched to these failures. Decisive-token supervision restores supervision balance by upweighting the cross-entropy contribution of pathology-related tokens and the EOS event, ensuring that content fidelity and termination are learned during training rather than imposed at decoding time. State-conditioned dynamic steering replaces fixed open-loop residuals with hidden-state-dependent adapters, allowing the injected signal to adapt as decoding drifts. Experiments on MIMIC-CXR and CheXpert Plus with two medical VLM backbones show that DIVE consistently ranks among the strongest methods across lexical and clinical-proxy metrics. Our method achieves the best BLEU-4, ROUGE-L, and RadGraph F1 in all dataset--backbone settings, while remaining competitive on coarse label-level CheXbert F1.

CodecCap: High-Fidelity Codec-Inspired Residual Modeling for Dense Video Captioning

Existing video captioning methods struggle to balance visual fidelity and redundancy: holistic captions are compact but lose fine-grained evidence, whereas segment-wise captions improve coverage but introduce heavy redundancy. We propose CodecCap, a codec-inspired framework for high-fidelity dense video captioning. Analogous to video codecs, CodecCap represents videos using keyframe and residual captions. Keyframe captions exhaustively encode stable visual context, while residual captions capture temporally only localized actions, motions and changes. This effectively preserves fine-grained visual evidence while reducing redundant descriptions. To quantify the fidelity of captions, we introduce VidCapQA, a caption-then-QA benchmark with 1,000 questions across 14 capability dimensions. Results on VidCapQA show that captions directly generated by strong VLMs still miss many visual details, highlighting caption representation as a critical bottleneck. Experiments show that CodecCap significantly surpasses direct captioning with the same underlying VLMs, suggesting keyframe-residual captioning a way for high-fidelity video-language supervision. We further use CodecCap to construct CodecVDC-100K, a large-scale dense captioning dataset with anchor, residual, scene-level, and video-level supervision.

Uncertainty-Aware Gaussian Map for Vision-Language Navigation

Vision-Language Navigation (VLN) requires an agent to navigate 3D environments following natural language instructions. During navigation, existing agents commonly encounter perceptual uncertainty, such as insufficient evidence for reliable grounding or ambiguity in interpreting spatial cues, yet they typically ignore such information when predicting actions. In this work, we explicitly model three forms of perceptual uncertainty (i.e., geometric, semantic, and appearance uncertainty) and integrate them into the agent's observation space to enable informed decision-making. Concretely, our agent first constructs a Semantic Gaussian Map (SGM), composed of differentiable 3D Gaussian primitives initialized from panoramic observations, that encodes both the geometric structure and semantic content of the environment. On top of SGM, geometric uncertainty is estimated through variational perturbations of Gaussian position and scale to assess structural reliability; semantic uncertainty is captured by perturbing Gaussian semantic attributes to reveal ambiguous interpretations; and appearance uncertainty is characterized by Fisher Information, which measures the sensitivity of rendered observations to Gaussian-level variations. These uncertainties are incorporated into SGM, extending it into a unified 3D Value Map, which grounds them as affordances and constraints that support reliable navigation. Comprehensive evaluations across multiple VLN benchmarks show the effectiveness of our agent.

3D Gaussian Map with Open-Set Semantic Grouping for Vision-Language Navigation

Vision-language navigation (VLN) requires an agent to traverse complex 3D environments based on natural language instructions, necessitating a thorough scene understanding. While existing works equip agents with various scene representations to enhance spatial awareness, they often neglect the complex 3D geometry and rich semantics in VLN scenarios, limiting the ability to generalize across diverse and unseen environments. To address these challenges, this work proposes a 3D Gaussian Map that represents the environment as a set of differentiable 3D Gaussians and accordingly develops a navigation strategy for VLN. Specifically, Egocentric Scene Map is constructed online by initializing 3D Gaussians from sparse pseudo-lidar point clouds, providing informative geometric priors for scene understanding. Each Gaussian primitive is further enriched through Open-Set Semantic Grouping operation, which groups 3D Gaussians based on their membership in object instances or stuff categories within the open world, resulting in a unified 3D Gaussian Map. Building on this map, Multi-Level Action Prediction strategy, which combines spatial-semantic cues at multiple granularities, is designed to assist agents in decision-making. Extensive experiments conducted on three public benchmarks (i.e., R2R, R4R, and REVERIE) validate the effectiveness of our method.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models

Diffusion Language Models (DLMs) have recently emerged as a promising alternative to autoregressive language models, offering stronger global awareness and highly parallel generation. However, post-training DLMs with standard Negative Evidence Lower Bound (NELBO)-based supervised fine-tuning remains inefficient: training reconstructs randomly masked tokens in a single step, whereas inference follows a confidence-guided, multi-step easy-to-hard denoising trajectory. Recent trajectory-based self-distillation methods exploit such inference trajectories mainly for sampling-step compression and acceleration, often improving decoding efficiency without substantially enhancing the model's underlying capability, and may even degrade performance under full diffusion decoding. In this work, we ask whether self-distilled trajectories can be used not merely for faster inference, but for genuine knowledge acquisition. Although these trajectories lie on the pretrained DLM's own distributional manifold and thus offer a potentially lower optimization barrier, we find that naively fine-tuning on them with standard NELBO objectives yields only marginal gains. To address this limitation, we propose \textbf{T}rajectory-\textbf{A}ligned optimization via \textbf{Bo}ltzmann \textbf{M}odeling (\textbf{TABOM}), a self-distilled trajectory-based post-training framework that aligns training with the easy-to-hard structure of inference. TABOM models the inference unmasking preference as a Boltzmann distribution over predictive entropies and derives a tractable pairwise ranking objective to align the model's certainty ordering with the observed decoding trajectory. Empirically, TABOM achieves substantial gains in new domains, expands the effective knowledge boundary of DLMs, and significantly mitigates catastrophic forgetting compared with standard SFT.

Beyond Text Prompts: Visual-to-Visual Generation as A Unified Paradigm

Humans often specify and create through visual artifacts: typography sheets, sketches, reference images, and annotated scenes. Yet modern visual generators still ask users to serialize this intent into text, a bottleneck that compresses signals like spatial structure, exact appearance, and glyph shape. We propose \textbf{\emph{visual-to-visual} (V2V)} generation, in which the user conditions a generative model with a visual specification page rather than a text prompt. The page is not an edit target, but a visual document that specifies the desired output. We introduce \textbf{V2V-Zero}, a training-free framework that exposes this interface in existing vision-language model (VLM) conditioned generators by replacing text-only conditioning with final-layer hidden states extracted from visual pages, exploiting the fact that the frozen VLM already maps both text and images into the generator's conditioning space. On GenEval, V2V-Zero reaches 0.85 with a frozen Qwen-Image backbone, closely matching its optimized text-to-image performance without fine-tuning. To evaluate the broader V2V space, we introduce \textbf{Simple-V2V Bench}, spanning seven visual-conditioning tasks and seven models, including GPT Image 2, Nano Banana 2, Seedream 5.0 Lite, open-weight baselines, and a video extension. V2V-Zero scores 32.7/100, outperforming evaluated open-weight image baselines and revealing a clear capability hierarchy: attribute binding is strong, content generation is unreliable, and structural control remains hard even for commercial systems. A HunyuanVideo-1.5 extension scores 20.2/100, showing the interface transfers beyond images. Mechanistic analysis shows the default reasoning path is primarily visually routed, with 95.0\% of conditioning-token attention mass on visual-page hidden states.