We introduce Piano2Pop, a music-expansion task that transforms piano MIDI into instrumental pop productions. Enabled by recent advances in music generation and polyphonic music transcription, our pseudo-supervised approach conditions a pretrained flow-matching model on piano rolls without aligned piano-pop supervision. We train on synthetic piano-instrumental pairs derived from pop recordings, comparing pair-free transcription, including function-selective (FST) and register-density (RDA) augmentations, with a pair-supervised piano-cover generator as pseudo-demo sources. On 476 testing real-world piano-cover/pop pairs, the pair-supervised approach achieves the best Frechet Audio Distance, Accompaniment Prompt Adherence, and spectral shape on real-piano inputs, while FST mitigates piano-heavy outputs in pair-free training and remains a promising alternative. All fine-tuned systems significantly outperform the zero-shot baselines, which suggests a role for task-specific modeling.

Complex camera motion is central to visual storytelling, yet translating cinematographic intent into controllable, executable camera trajectories remains challenging. We introduce FilmFlow, an agentic framework that converts natural-language instructions or reference videos into explicit camera trajectories for dynamic 3D environments. To generate these trajectories, a Director agent constructs executable camera plans by composing high-level motions from concurrent atomic operations that jointly control translation, rotation, and framing. The Director is supported by three specialized agents: an Interpreter that extracts scene-grounded cinematographic intent, a Scout that selects initial viewpoints, and a Critic that evaluates rendered results and provides visual feedback for iterative plan refinement. We also introduce CinemaBench, comprising 150 Blender scenes from self-created and licensed sources, with five camera instructions per scene for 750 text-directed tasks and 60 reference videos associated with a subset of scenes. CinemaBench supports evaluation of both text-directed camera generation and video reference-directed camera generation. Across a diverse set of evaluated baselines, FilmFlow achieves the strongest benchmark performance and the highest user preference, demonstrating effective spatial reasoning, temporal coordination, and visual composition for executable 3D cinematography.

Video diffusion models have learned rich 3D/4D priors, making them promising for scene generation and video re-rendering. However, their use in spatial tasks is limited by imprecise camera control, spatial and temporal inconsistencies, and entangled camera motion with scene dynamics. Existing approaches, such as task-specific fine-tuning and post-process warping, often introduce visual artifacts, generalize poorly, or incur high computational costs. We propose WorldForge V2 to achieve accurate camera control while preserving the generative capabilities of pretrained video models. We first develop a training-free guidance framework using warped references to iteratively refine generation along a target camera path. Optical-flow analysis identifies motion-related latent channels for selective guidance, helping separate motion control from appearance. A dual-path strategy further compares guided and unguided predictions to correct artifacts from imperfect references. Together, these components guide viewpoint changes while preserving scene appearance and object motion. To reduce refinement costs, v-cache approximates the correction using the preceding denoising prediction, avoiding an additional model evaluation. We further extend motion localization from latent channels to network blocks and introduce Trajectory LoRA, which concentrates adaptation on blocks most responsive to trajectory guidance. A two-stage training strategy teaches these adapters to denoise the states encountered during guided generation, using limited supervision effectively. This enables reliable camera control with very little training data, with a single training scene already supporting generalization to unseen scenes. Quantitative and qualitative evaluations across multiple datasets show that our method achieves state-of-the-art generation quality and trajectory accuracy in camera-controlled video generation.

The performance of medical image segmentation depends on a large amount of annotated data, and most segmentation models experience a significant drop in performance in low-sample-size scenarios. Existing semi-supervised and weakly supervised methods rely on specific network architectures, while traditional multi-view-assisted segmentation methods require strictly paired samples, which limits their clinical applications. To address these issues, we propose DPIF, a general-purpose plug-and-play dual-path interaction framework compatible with arbitrary encoder-decoder segmentation networks, which leverages cross-view anatomical complementarity to reduce annotation reliance. DPIF first performs Sinkhorn optimal transport-based cross-view distribution alignment to establish global semantic correspondence without sample-level pairing. It then adopts conditional mutual information-guided feature decoupling to enable bidirectional knowledge transfer only within the shared semantic space, suppressing view-specific noise. Finally, persistent homology-based topological regularization encodes anatomical invariants as unsupervised priors to mitigate overfitting. Experiments were conducted using 24 baseline models on a private multicenter echocardiography dataset and two public datasets. The results show that DPIF-enhanced models outperform single-view baseline models when trained on comparable amounts of data. Notably, most dual-path variants trained on 40\% - 60\% of the data achieve performance comparable to that of single-view models trained on the full dataset. This demonstrates that DPIF provides a general-purpose and scalable solution for data-scarce multi-view medical image segmentation problems.

Systems that aim to help a user engage with viewpoints other than their own have to decide how different those viewpoints should be. Viewpoints are mainly represented on a scalar scale, too coarse to distinguish viewpoints that disagree with the user about different things. We introduce a selection policy in which a bandit sets how far viewpoints may sit from the user, and the policy selects the most novel viewpoint within that bound. We vary only its stance encoder, comparing a scalar score with Perspectivized Stance Vectors, which break a position into separate stances on concepts. We integrate it inside a dialog system and run a between-subjects study (N=63). Concept-level stance produces more varied exposure sequences and broader coverage of the topic's positions, but does not change how deeply users justify viewpoints or how accurately they reconstruct them. Finally, we analyze user--viewpoint relations at the concept level, showing that users reconstruct a viewpoint least accurately on concepts that one side took no position on, rather than on concepts where the two disagreed. Our findings open up opportunities for dialog systems that support engagement with alternative viewpoints by acting on which concepts a user and a viewpoint disagree on, rather than on distance alone.

Frontier coding agents are becoming increasingly adept at 3D modeling. Yet, they still face challenges when building objects meant to be assembled in the physical world, often creating invalid assemblies with floating, colliding, or disconnected parts. We argue that providing agents with tools for assembling builds and verifying their physical feasibility is sufficient for them to produce physically valid assemblies that still adhere to input prompts. Focusing on the domain of LEGO brick builds, we present BrickWright, a framework for generating physically feasible brick builds from text or image prompts using pre-trained agents, where a build is physically feasible if it uses only real parts, has no colliding or floating parts, and forms a connected structure if possible. BrickWright guides agents to create builds by writing code with BrickLayer, a Python toolkit with two main components: an ergonomic brick assembly API that halves inference cost compared to working in raw LDraw, and a validator that provides feedback on physical feasibility. Whereas baseline agents achieve physical validity rates ranging from only 9% (GPT-6 Luna) to 69% (GPT-6 Astra), BrickWright-guided agents achieve 100% validity on a sample of 512 prompts, while improving prompt adherence for lightweight agents and maintaining it for stronger agents. Additionally, they outperform specialized models on the text-to-brick task. Code is available on our project page: https://avalovelace1.github.io/brickwright/

Bashkir is a low-resource agglutinative language written in Cyrillic and remains poorly represented in modern LLMs. We present an open resource suite and a systematic benchmark of adaptation methods: the Bashkir Web Corpus (71,567 documents, 46.9M tokens, 16 sources) and three labelled datasets for binary, multiclass and multilabel text classification; the benchmark covers the first two. Experiments use eight architectures (82M-8B: DistilGPT2, GPT-2 base/medium, Phi-3-mini, Mistral-7B, YandexGPT-5-Lite-8B, mBERT, XLM-R) and three adaptation groups (full fine-tuning, QLoRA, in-context learning), plus continual pretraining (CPT). (1) QLoRA on 3.8-8B models outperforms encoder-only fine-tuning on binary classification: YandexGPT-5-Lite-8B with CPT reaches macro-F1 0.748 vs 0.653 (XLM-R) and 0.650 (mBERT); pairwise differences are significant after Holm correction (p<0.001). (2) YandexGPT-5-Lite-8B significantly outperforms Mistral-7B and Phi-3-mini on multiclass classification, BPB and native-speaker ratings (mean 3.28 vs 2.52 and 2.22; n=100; alpha=0.69-0.77; p<0.05); on binary classification its QLoRA advantage is not significant (p>=0.084). (3) CPT effects depend on model and task: perplexity improves for Phi-3-mini (+0.58) and YandexGPT-5-Lite-8B (+0.33) but worsens for Mistral-7B (-1.15, p<0.001); on binary classification CPT helps Mistral-7B most (+4.0 macro-F1). (4) Tokeniser fertility on Bashkir varies 2.67x (2.92-7.80) and tracks adaptation quality, while perplexity across tokenisers is not comparable. Cyrillic tokenisers with Russian pretraining are preferable; LLM judges reproduce native ratings for grammar and coherence (rho=0.33-0.46) but not language correctness (rho=0.16, p=0.11); native evaluation remains necessary. All artefacts are open-licensed.

Accurate hippocampal segmentation can be a useful tool for diagnosing and monitoring neurological conditions such as Alzheimer's disease and epilepsy. While numerous automated segmentation methods exist, their clinical adoption remains limited. Reliable uncertainty assessment can enhance trust and facilitate clinical translation. This study evaluates ensembles of five heterogeneous hippocampal segmentation methods - InnerEye, ASHS, FastSurfer, HippoSeg, and FreeSurfer - across two dementia datasets and one epilepsy dataset. The sub-ensemble containing InnerEye, FastSurfer, and HippoSeg emerged as both accurate and efficient, highlighting the feasibility of balancing computational cost and performance. Additionally, ensemble-derived uncertainty quantification with sample variance, mutual information, and predictive entropy is shown to reduce inaccurate segmentations by flagging low-confidence cases, potentially providing a mechanism for automatically escalating ambiguous cases for expert assessment. Lastly, this study explores the downstream clinical utility of ensemble-derived uncertainty, finding a significant correlation with motion artefact severity and a modest contribution to Alzheimer's disease classification.

\emph{Continuous-space} attacks find prompts that trigger malicious behaviors, such as overthinking, in black-box LLMs by sampling or optimizing over a low-dimensional Gaussian latent space and decoding it to text through a \emph{random mapping} and nearest-token lookup. Because the random mapping is not learned from language, its prompts can be highly unnatural, and as such easily detectable through input guardrails, and the risk estimates they yield are not grounded in natural prompts. In this paper, we demonstrate that the same continuous latent-space framework can be coupled directly to a learned generative distribution over language, a continuous diffusion language model (dLLM), which removes the artificial random mapping while preserving the standard-Gaussian latent formulation and the downstream sampling or optimization procedure. We evaluate this approach under two settings: sampling-based estimation using \emph{RareTrap} and optimization-based search using \emph{ThinkTrap}. We find that character-level perplexity drops from $10^3$--$10^7$ to 3--5 in RareTrap and from 20--28 to 4.3--5.4 in ThinkTrap. We also find that model risk estimates can differ by an order of magnitude across the two mappings.

Learnable Representations (LRs) can fit parametric families of functions to diverse kinds of signals. These emergent neural-native data formats are gathering interest in the scientific community due to their compactness, resolution-agnosticism and amenability to direct neural processing. On the other hand, gigapixel images are becoming increasingly widespread across a variety of scientific, cultural, and industrial domains. In this paper, we present GigaBench, the first benchmark and experimental evaluation focused on deploying LRs with gigapixel imagery. GigaBench includes images collected, acquired, and synthetically rendered across diverse domains, and addresses image compression and super-resolution. We adapt a representative set of LRs, spanning Implicit, Hybrid, and Explicit methods, so as to operate reliably at the gigapixel scale on consumer hardware. Through systematic evaluation across reconstruction quality, model size, compression and inference times, we identify consistent trends across methods and suggest actionable guidance for future investigation.

Video object removal and injection are reciprocal editing operations between object-present and object-absent video states, yet they differ substantially in training difficulty. Removal can be effectively bootstrapped from video inpainting and further adapted to erase object-related interaction effects. Injection, however, requires large-scale paired supervision to model object appearance, dynamics, and scene-dependent effects, while perfectly aligned real-world pairs are difficult to collect and synthetic data lacks sufficient realism and diversity. To address this challenge, we present UniVOE, a removal-driven framework for training both video object removal and injection models. We first train an effect-aware remover by transferring video inpainting priors and finetuning on object-present/object-absent pairs. The trained remover converts real object-present videos into object-absent counterparts, creating large-scale paired supervision for injection. An injection model is trained on these pairs in the reverse direction to recover objects together with their dynamics and interaction effects. Moreover, since pixel-level reconstruction alone cannot adequately capture perceptual realism, we introduce a reward-based post-training method that aligns injection results with human preferences using a proprietary reward model. Experiments against strong open-source and commercial systems demonstrate that UniVOE achieves state-of-the-art performance on both object removal and injection, particularly in challenging interaction-effect cases.

Progressive image compression reconstructs images from prefixes of a single bitstream and therefore involves sequential latent inference under partial observations. Existing trit-plane codecs mainly treat decoded trits as discrete symbols for probability prediction, without fully exploiting their role as interval constraints on the underlying continuous latents. We propose bound-conditioned latent inference (BLI), a framework that reformulates progressive trit-plane coding as sequential latent inference under shrinking interval constraints. At each coding step, the trits decoded so far define lower and upper bounds for each latent element. BLI uses the center and width of these bounds, together with hyperprior information shared by the encoder and decoder, to jointly refine the Gaussian parameters $(\mu,\sigma)$ for entropy modeling and the latent estimate $\hat{y}$ for reconstruction. As additional trits are decoded, the feasible intervals shrink monotonically, yielding tighter constraints for the next inference step and enabling flexible in-plane refinement schedules. Experiments on Kodak, CLIC, and JPEG-AI show that BLI achieves state-of-the-art rate-distortion performance among progressive image codecs, reducing BD-rate by $17.78\%$ over DPICT and by $7.96\%$ over CTC on Kodak, while replacing CTC's plane-specific predictors with a shared model that uses about $5.3\times$ fewer parameters and achieves lower latency than CTC.

Measuring animal distance and motion in metric units underpins abundance estimation, morphometrics, and movement ecology, yet monocular video lacks metric scale and wildlife datasets lack metric ground truth. We present WildDepth 2, extending the synchronized RGB-LiDAR WildDepth dataset in three directions. (i) Imaging radar: 37 RGB-LiDAR-4D-radar sequences (19,716 frames) with per-point Doppler velocity and a measured error budget, to our knowledge the first imaging-radar wildlife recordings. (ii) Benchmarking: a frozen, checksummed hidden test set for RGB-only distance estimation and RGB+sparse-LiDAR depth completion, evaluated separately on animal and background pixels. (iii) Motion and tracking: metric 3D trajectories obtained by lifting 2D tracks using LiDAR, radar, or monocular depth. Across 48,723 animal frames, object-level radar calibration improves monocular depth over scene-level LiDAR calibration without requiring LiDAR at inference (AbsRel 0.120 vs. 0.198), although animal-level LiDAR remains more accurate (0.052). Across 431 tracks, once-per-track radar scaling reduces 3D position error four-fold (2.20 to 0.58 m) and distance-sampling detection-function bias from -13% to -2%, matching once-per-track LiDAR calibration. Transferring radar Doppler onto LiDAR produces motion masks 3.7 times denser than radar alone at 72% precision, reduces moving-animal LiDAR accumulation error by 37%, and estimates radial speed (r = 0.60), albeit with approximately 50% underestimation.

Many questions about a video concern one physical object. Where does the ball end up after the cups are shuffled? Which card is the queen? How often was the mug covered? Video-language models (Video-LMs) recognise such objects in single frames but do not keep them apart over time. On real shell-game videos, open models from 8B to 235B parameters, their thinking variants, a reinforcement-learned tool agent and three training-free tool agents all stay within ten points of chance. We separate semantic identity binding from temporal identity maintenance. An object's identity should be fixed at a moment when the evidence for it is visible, and carried afterwards by a tracker. \emph{Track, Then Bind} implements this principle without training. A promptable video tracker follows every candidate object and draws it with a track number. A frozen vision-language model answers a static question about the identifying evidence, which binds the target to a track. The answer is then derived from the tracked state in text, without asking the model to reinterpret the original video during read-out. A single configuration covers all benchmarks. With Qwen3-VL-32B it solves both VET-Bench tasks, where a fine-tuned trajectory model reaches 92\% and 90\% and the same VLM voting over 16 samples stays at 30--32\%. It answers 55.4\% of the hardest Perception Test cup games, where the best published model answers 41.5\%, and, using track-derived timelines, 48.6\% of TOC-Bench questions, against 37.1\% for the same model answering directly. Drawing the same tracks on the video and asking the question directly falls 12--19 points short of the agent on real cup games.

Deep research agents synthesize open-web evidence into long reports, but current benchmarks do not evaluate research centered on a source video. We introduce Video-Centered Deep Research Report Generation. Given a video and user request, an agent identifies research questions, retrieves external multimodal evidence, and produces an interactive report linked to relevant video moments. This task has direct practical value because it helps users locate relevant moments, verify claims, reproduce demonstrated procedures, and make informed decisions from video content. We present a skill-based workflow and OmniDR-Bench for this task. For evaluation, we propose Omni Atomic Rubric Trees (Omni-ARTs). Each tree contains three dimensions, 23 shared directions, and task-specific atomic binary criteria. The directions test audiovisual grounding, multimodal evidence use, and interactive presentation. Audited Rubric Construction (ARC) builds these trees through independent evidence collection, automated checks, behavioral calibration, and iterative human review. OmniDR-Bench contains 50 Chinese and English tasks across 19 realworld subcategories. It includes 6,414 criteria. Across 18 agent configurations, the best system scores 63.3 out of 100. Current agents still need broader content coverage, stronger causal and logical analysis across modalities, and more accurate citation support. We further analyze models, harnesses, skill configurations, video categories, and research trajectories. The code and data are released at https://github.com/marinero4972/OmniDR-Bench.

Large Language Models (LLMs) can generate UML class diagrams from natural language requirements, but hallucinations may compromise the correctness and completeness of the resulting diagrams. Existing evaluations mostly assess the final diagram, without examining the intermediate traces of reasoning-capable LLMs, which can reveal where these hallucinations arise. We develop an empirical taxonomy of eleven hallucination sub-types organised into three dimensions: Prompt Faithfulness (deviations between requirements and reasoning), Code Faithfulness (discrepancies between reasoning and generated PlantUML code), and Reasoning Quality (problems within the reasoning). The taxonomy was derived from 60 manually annotated DeepSeek-R1 traces, applied to 120 further DeepSeek-R1 traces through a dual-LLM annotation pipeline, and examined on 20 DeepSeek-V4-Pro traces. Code Faithfulness was the most frequent dimension for DeepSeek-R1 in both datasets, whereas Prompt Faithfulness dominated for DeepSeek-V4-Pro, suggesting model-dependent failure patterns. In the manually annotated traces, reasoning-trace length showed no significant monotonic association with hallucination frequency, whereas requirement complexity was negatively associated with it, particularly for Prompt Faithfulness errors. In a mitigation experiment on 13 Golden UML ModelSet cases with three Qwen3-based models, adding Prompt Faithfulness and Reasoning Quality constraints to the generation prompt raised the pooled mean F1 score by 4.0 percentage points, whereas a post-hoc Code Faithfulness review provided no consistent further benefit. Relationship modelling remained the lowest-scoring element throughout. These results suggest that localising hallucinations within the generation process can inform targeted, prompt-based mitigation. Whether these findings generalise beyond the DeepSeek and Qwen3 model families remains to be tested.

Vector quantization (VQ), in particular lattice-based methods, offer strong rate-distortion trade-offs for low-bit large language models (LLMs), yet their behavior under quantization-aware training (VQ-QAT) remains poorly understood. We scale lattice VQ-QAT to billion-parameter LLMs and multi-billion-token training regimes, and introduce SQuAT, a shape-gain VQ-QAT approach trained with a separate straight-through estimator (STE) for the shape and gain. SQuAT decomposes weights into direction and magnitude: normalized directions are quantized using an $E_8$-derived spherical codebook, while gains are quantized independently with low-bit scalar quantizers. We show that, unlike a standard STE applied to the full quantizer, which ignores the shape-gain structure, these separate STEs induce tangent-space updates for directions, yielding an implicit form of spherical (Riemannian) optimization. To enable scalability, we develop a distributed exact nearest-neighbor assignment scheme, in which workers quantize disjoint weight blocks and communicate only discrete indices, reducing VQ-QAT training time by 12.8$\times$ and allowing us to scale it to 10B tokens. Across instruction-tuned LLaMA-3.2-1B/3B, Qwen3-4B, and base Qwen3-1.7B, SQuAT consistently outperforms standard VQ-QAT STE under identical quantizers and initialization, and achieves SOTA VQ-QAT accuracy.

Activation verbalizers translate the internal representations of large language models into human-readable text. The recently proposed natural language autoencoders (NLAs) learn this by reconstructing activations through a natural language bottleneck. However, it remains unclear how well these methods generalize beyond the setting they were trained for. Here, we study this question for NLAs along four closely related questions: (i) Do NLA verbalizations exhibit compositional structure with respect to their input? (ii) Do NLAs generalize to finetuned versions of the model they were trained for? (iii) Can NLAs recover finetuning objectives in model diffing? (iv) Can NLAs be specialized for model diffing? Across four models from three families, our experiments provide evidence supporting a largely positive answer to all four questions. Specifically, verbalizations of composed analogy activations mostly name the target while rarely mentioning the subtracted word, and an NLA can be reused on lightweight finetunes of its original model without retraining, with reconstruction quality degrading noticeably only for the largest model. Verbalizing activation differences between Taboo model organisms and their original models recovers the concealed secret word for most organisms, and reinforcement learning on activation differences further improves this recovery on held-out organisms. We also find that NLAs can recover the finetuning objective without the finetuned model generating any token, since the most informative token positions precede the user prompt. NLAs do not yet match state-of-the-art model diffing methods on the emergent misalignment detection task, but outperform a blackbox baseline. Our findings suggest that NLAs can meaningfully verbalize differences in activation space, rendering NLAs a promising direction for future work.

Large language models (LLMs) are increasingly used to generate domain-specific commercial & medical content (e.g., claims, statements, and promotional phrases) in regulated industries such as pharmaceuticals. However, ensuring its regulatory compliance, factual accuracy, and audience-specific personalization remains a major challenge. We report a production case study asking whether moving compliance and personalization signal from prompt-level rules into retrieval time structured context improves pharmaceutical claims generation, using Composer, a deployed internal tool built on a Golden Data Model (GDM) of 1,867 pharmaceutical claims spanning four products. The GDM integrates claim metadata, references, audience labels, material type, usage history, Match Text Variant (MTV) links, and a six dimension quality score (6C). Across six product-audience segments, the context pipeline improves intended indication (+29%), intended content type (+62%) and intended target audience (+67%), 6C quality score (+86%), and claim reuse (+34%). Production log analysis over the deployment period shows a 29.5% reduction in weekly API cost. We report this as descriptive deployment evidence. This work is a systems and data architecture contribution: it shows that in a regulated, high-stakes domain, restructuring claim data for retrieval-time filtering is a more scalable lever than expanding prompt-level rules, and documents the engineering path data cleaning, graph linking, and quality scoring.

While there is increasing evidence that words are stored in the mental lexicon with some phonetic detail, there are open questions about exactly which phonetic details are stored and whether they are functionally relevant for spoken word recognition. Word-level phonetic cues, such as word duration, provide an appropriate test case. Across languages, including Mandarin Chinese, high frequency words are shorter than low frequency words. Using a homophone ordering task, we investigate whether differences in word duration impact word recognition. Mandarin Chinese was examined since it has abundant disyllabic homophones. Our results indicate that participants were able to use word duration to recognize the order of homophone pairs, selected to vary in lexical frequency. Both with high noise levels and when no other cues were available, participants mapped the shorter duration auditory stimulus to the higher frequency word. The results provide evidence that word duration can directly cue the identity of words, suggesting that it may be a phonetic detail incorporated into the lexical representation. We discuss this direct cueing account alongside alternative accounts of how word duration may modulate word recognition.