Pts3D-LLM: Studying the Impact of Token Structure for 3D Scene Understanding With Large Language Models

Effectively representing 3D scenes for Multimodal Large Language Models (MLLMs) is crucial yet challenging. Existing approaches commonly only rely on 2D image features and use varied tokenization approaches. This work presents a rigorous study of 3D token structures, systematically comparing video-based and point-based representations while maintaining consistent model backbones and parameters. We propose a novel approach that enriches visual tokens by incorporating 3D point cloud features from a Sonata pretrained Point Transformer V3 encoder. Our experiments demonstrate that merging explicit 3D features significantly boosts performance. Furthermore, we show that point-based token structures can rival video-based ones when the points are cleverly sampled and ordered. Our best models from both structures achieve state-of-the-art results on multiple 3D understanding benchmarks. We emphasize our analysis of token structures as a key contribution, alongside transparent reporting of results averaged over multiple seeds, a practice we believe is vital for robust progress in the field.

AssetDropper: Asset Extraction via Diffusion Models with Reward-Driven Optimization

Recent research on generative models has primarily focused on creating product-ready visual outputs; however, designers often favor access to standardized asset libraries, a domain that has yet to be significantly enhanced by generative capabilities. Although open-world scenes provide ample raw materials for designers, efficiently extracting high-quality, standardized assets remains a challenge. To address this, we introduce AssetDropper, the first framework designed to extract assets from reference images, providing artists with an open-world asset palette. Our model adeptly extracts a front view of selected subjects from input images, effectively handling complex scenarios such as perspective distortion and subject occlusion. We establish a synthetic dataset of more than 200,000 image-subject pairs and a real-world benchmark with thousands more for evaluation, facilitating the exploration of future research in downstream tasks. Furthermore, to ensure precise asset extraction that aligns well with the image prompts, we employ a pre-trained reward model to fulfill a closed-loop with feedback. We design the reward model to perform an inverse task that pastes the extracted assets back into the reference sources, which assists training with additional consistency and mitigates hallucination. Extensive experiments show that, with the aid of reward-driven optimization, AssetDropper achieves the state-of-the-art results in asset extraction. Project page: AssetDropper.github.io.

Unleashing the Power of Intermediate Domains for Mixed Domain Semi-Supervised Medical Image Segmentation

Both limited annotation and domain shift are prevalent challenges in medical image segmentation. Traditional semi-supervised segmentation and unsupervised domain adaptation methods address one of these issues separately. However, the coexistence of limited annotation and domain shift is quite common, which motivates us to introduce a novel and challenging scenario: Mixed Domain Semi-supervised medical image Segmentation (MiDSS), where limited labeled data from a single domain and a large amount of unlabeled data from multiple domains. To tackle this issue, we propose the UST-RUN framework, which fully leverages intermediate domain information to facilitate knowledge transfer. We employ Unified Copy-paste (UCP) to construct intermediate domains, and propose a Symmetric GuiDance training strategy (SymGD) to supervise unlabeled data by merging pseudo-labels from intermediate samples. Subsequently, we introduce a Training Process aware Random Amplitude MixUp (TP-RAM) to progressively incorporate style-transition components into intermediate samples. To generate more diverse intermediate samples, we further select reliable samples with high-quality pseudo-labels, which are then mixed with other unlabeled data. Additionally, we generate sophisticated intermediate samples with high-quality pseudo-labels for unreliable samples, ensuring effective knowledge transfer for them. Extensive experiments on four public datasets demonstrate the superiority of UST-RUN. Notably, UST-RUN achieves a 12.94% improvement in Dice score on the Prostate dataset. Our code is available at https://github.com/MQinghe/UST-RUN

LAFR: Efficient Diffusion-based Blind Face Restoration via Latent Codebook Alignment Adapter

Blind face restoration from low-quality (LQ) images is a challenging task that requires not only high-fidelity image reconstruction but also the preservation of facial identity. While diffusion models like Stable Diffusion have shown promise in generating high-quality (HQ) images, their VAE modules are typically trained only on HQ data, resulting in semantic misalignment when encoding LQ inputs. This mismatch significantly weakens the effectiveness of LQ conditions during the denoising process. Existing approaches often tackle this issue by retraining the VAE encoder, which is computationally expensive and memory-intensive. To address this limitation efficiently, we propose LAFR (Latent Alignment for Face Restoration), a novel codebook-based latent space adapter that aligns the latent distribution of LQ images with that of HQ counterparts, enabling semantically consistent diffusion sampling without altering the original VAE. To further enhance identity preservation, we introduce a multi-level restoration loss that combines constraints from identity embeddings and facial structural priors. Additionally, by leveraging the inherent structural regularity of facial images, we show that lightweight finetuning of diffusion prior on just 0.9% of FFHQ dataset is sufficient to achieve results comparable to state-of-the-art methods, reduce training time by 70%. Extensive experiments on both synthetic and real-world face restoration benchmarks demonstrate the effectiveness and efficiency of LAFR, achieving high-quality, identity-preserving face reconstruction from severely degraded inputs.

Robot Operation of Home Appliances by Reading User Manuals

Operating home appliances, among the most common tools in every household, is a critical capability for assistive home robots. This paper presents ApBot, a robot system that operates novel household appliances by "reading" their user manuals. ApBot faces multiple challenges: (i) infer goal-conditioned partial policies from their unstructured, textual descriptions in a user manual document, (ii) ground the policies to the appliance in the physical world, and (iii) execute the policies reliably over potentially many steps, despite compounding errors. To tackle these challenges, ApBot constructs a structured, symbolic model of an appliance from its manual, with the help of a large vision-language model (VLM). It grounds the symbolic actions visually to control panel elements. Finally, ApBot closes the loop by updating the model based on visual feedback. Our experiments show that across a wide range of simulated and real-world appliances, ApBot achieves consistent and statistically significant improvements in task success rate, compared with state-of-the-art large VLMs used directly as control policies. These results suggest that a structured internal representations plays an important role in robust robot operation of home appliances, especially, complex ones.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

The rapid advancement of Large Multimodal Models (LMMs) for 2D images and videos has motivated extending these models to understand 3D scenes, aiming for human-like visual-spatial intelligence. Nevertheless, achieving deep spatial understanding comparable to human capabilities poses significant challenges in model encoding and data acquisition. Existing methods frequently depend on external depth sensors for geometry capture or utilize off-the-shelf algorithms for pre-constructing 3D maps, thereby limiting their scalability, especially with prevalent monocular video inputs and for time-sensitive applications. In this work, we introduce VLM-3R, a unified framework for Vision-Language Models (VLMs) that incorporates 3D Reconstructive instruction tuning. VLM-3R processes monocular video frames by employing a geometry encoder to derive implicit 3D tokens that represent spatial understanding. Leveraging our Spatial-Visual-View Fusion and over 200K curated 3D reconstructive instruction tuning question-answer (QA) pairs, VLM-3R effectively aligns real-world spatial context with language instructions. This enables monocular 3D spatial assistance and embodied reasoning. To facilitate the evaluation of temporal reasoning, we introduce the Vision-Spatial-Temporal Intelligence benchmark, featuring over 138.6K QA pairs across five distinct tasks focused on evolving spatial relationships. Extensive experiments demonstrate that our model, VLM-3R, not only facilitates robust visual-spatial reasoning but also enables the understanding of temporal 3D context changes, excelling in both accuracy and scalability.

MIND-Edit: MLLM Insight-Driven Editing via Language-Vision Projection

Recent advances in AI-generated content (AIGC) have significantly accelerated image editing techniques, driving increasing demand for diverse and fine-grained edits. Despite these advances, existing image editing methods still face challenges in achieving high precision and semantic accuracy in complex scenarios. Recent studies address this issue by incorporating multimodal large language models (MLLMs) into image editing pipelines. However, current MLLM-based methods mainly rely on interpreting textual instructions, leaving the intrinsic visual understanding of large models largely unexplored, thus resulting in insufficient alignment between textual semantics and visual outcomes. To overcome these limitations, we propose MIND-Edit, an end-to-end image-editing framework integrating pretrained diffusion model with MLLM. MIND-Edit introduces two complementary strategies: (1) a text instruction optimization strategy that clarifies ambiguous user instructions based on semantic reasoning from the MLLM, and (2) an MLLM insight-driven editing strategy that explicitly leverages the intrinsic visual understanding capability of the MLLM to infer editing intent and guide the diffusion process via generated visual embeddings. Furthermore, we propose a joint training approach to effectively integrate both strategies, allowing them to reinforce each other for more accurate instruction interpretation and visually coherent edits aligned with user intent. Extensive experiments demonstrate that MIND-Edit outperforms state-of-the-art image editing methods in both quantitative metrics and visual quality, particularly under complex and challenging scenarios.

AvatarShield: Visual Reinforcement Learning for Human-Centric Video Forgery Detection

The rapid advancement of Artificial Intelligence Generated Content (AIGC) technologies, particularly in video generation, has led to unprecedented creative capabilities but also increased threats to information integrity, identity security, and public trust. Existing detection methods, while effective in general scenarios, lack robust solutions for human-centric videos, which pose greater risks due to their realism and potential for legal and ethical misuse. Moreover, current detection approaches often suffer from poor generalization, limited scalability, and reliance on labor-intensive supervised fine-tuning. To address these challenges, we propose AvatarShield, the first interpretable MLLM-based framework for detecting human-centric fake videos, enhanced via Group Relative Policy Optimization (GRPO). Through our carefully designed accuracy detection reward and temporal compensation reward, it effectively avoids the use of high-cost text annotation data, enabling precise temporal modeling and forgery detection. Meanwhile, we design a dual-encoder architecture, combining high-level semantic reasoning and low-level artifact amplification to guide MLLMs in effective forgery detection. We further collect FakeHumanVid, a large-scale human-centric video benchmark that includes synthesis methods guided by pose, audio, and text inputs, enabling rigorous evaluation of detection methods in real-world scenes. Extensive experiments show that AvatarShield significantly outperforms existing approaches in both in-domain and cross-domain detection, setting a new standard for human-centric video forensics.

Teach2Eval: An Indirect Evaluation Method for LLM by Judging How It Teaches

Recent progress in large language models (LLMs) has outpaced the development of effective evaluation methods. Traditional benchmarks rely on task-specific metrics and static datasets, which often suffer from fairness issues, limited scalability, and contamination risks. In this paper, we introduce Teach2Eval, an indirect evaluation framework inspired by the Feynman Technique. Instead of directly testing LLMs on predefined tasks, our method evaluates a model's multiple abilities to teach weaker student models to perform tasks effectively. By converting open-ended tasks into standardized multiple-choice questions (MCQs) through teacher-generated feedback, Teach2Eval enables scalable, automated, and multi-dimensional assessment. Our approach not only avoids data leakage and memorization but also captures a broad range of cognitive abilities that are orthogonal to current benchmarks. Experimental results across 26 leading LLMs show strong alignment with existing human and model-based dynamic rankings, while offering additional interpretability for training guidance.

Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning

Graphical User Interface (GUI) agents have made substantial strides in understanding and executing user instructions across diverse platforms. Yet, grounding these instructions to precise interface elements remains challenging, especially in complex, high-resolution, professional environments. Traditional supervised finetuning (SFT) methods often require large volumes of diverse data and exhibit weak generalization. To overcome these limitations, we introduce a reinforcement learning (RL) based framework that incorporates three core strategies: (1) seed data curation to ensure high quality training samples, (2) a dense policy gradient that provides continuous feedback based on prediction accuracy, and (3) a self evolutionary reinforcement finetuning mechanism that iteratively refines the model using attention maps. With only 3k training samples, our 7B-parameter model achieves state-of-the-art results among similarly sized models on three grounding benchmarks. Notably, it attains 47.3\% accuracy on the ScreenSpot-Pro dataset, outperforming much larger models, such as UI-TARS-72B, by a margin of 24.2\%. These findings underscore the effectiveness of RL-based approaches in enhancing GUI agent performance, particularly in high-resolution, complex environments.