SuperVoxelGPT: Adaptive and Ordered 3D Tokenization for Autoregressive Shape Generation

Autoregressive multimodal large language models (MLLMs) enable 3D generation but struggle to scale to high-resolution shapes due to inadequate 3D tokenizations. Compact set-based representations discard deterministic spatial ordering, leading to ambiguous sequence prediction, while uniform or octree-based voxel grids preserve ordering at the cost of severe redundancy and excessively long sequences. This structural trade-off limits stable and efficient autoregressive 3D generation. We present SuperVoxelGPT, a representation-first framework that resolves this tension through adaptive and deterministically ordered supervoxel tokenization. Given a prompt, we first predict a coarse geometric saliency distribution and construct a shape-adaptive supervoxel partition using saliency-guided centroidal Voronoi tessellation, allocating fine-grained cells to complex regions and larger cells to smooth regions. Conditioned on the text and ordered supervoxel layout, we introduce a SuperVoxelVAE and fine-tune a pretrained MLLM to autoregressively generate supervoxel tokens. Experiments on Trellis-500K show that SuperVoxelGPT reduces token sequence length to 12.8% of uniform voxel tokenization while achieving state-of-the-art generation quality and an average 10$\times$ speedup over prior methods.

Sparse-LiDAR Prompting of Monocular Geometry Foundations: An Empirical Study Toward Long-Range Driving Depth

Sparse-LiDAR-prompted depth foundation models (PromptDA, Prior Depth Anything, DMD3C) have shown strong results on indoor scenes or within KITTI's standard 80-meter evaluation cap. However, two limitations remain: (i) systematic distance-stratified evaluation in long-range driving regimes (50-150 m) is largely absent; (ii) prior approaches built on disparity-based foundations rely on pre-interpolated dense priors, leaving truly sparse LiDAR injection on point-map foundations (e.g., MoGe-2, NeurIPS 2025) unexplored. We present SLIM (Sparse-LiDAR Injected Monocular geometry), the first adaptation of MoGe-2 to accept truly sparse LiDAR input. SLIM integrates a partial-convolution sparse encoder with a multi-scale fusion neck that fuses LiDAR features into the point-map decoder at five scales. We adopt density-agnostic training (random injection ratio in [0.005, 0.30]) so a single model serves diverse input densities. On Virtual KITTI and CARLA, SLIM reduces the absolute relative error of the MoGe-2 baseline by approximately 39-51% at 100-150 m. Ablation across six injection ratios shows partial-convolution injection improves both AbsRel and RMSE on Virtual KITTI in all six settings; on CARLA, AbsRel improves in five of six settings (one near-tie at 0.015 differs by 0.0013), and RMSE is comparable across encoders, with partial-convolution improving in three settings (by up to 0.31 unit) and losing by at most 0.11 unit in the other three.

Latent Bridge: Feature Delta Prediction for Efficient Dual-System Vision-Language-Action Model Inference

Dual-system Vision-Language-Action (VLA) models achieve state-of-the-art robotic manipulation but are bottlenecked by the VLM backbone, which must execute at every control step while producing temporally redundant features. We propose Latent Bridge, a lightweight model that predicts VLM output deltas between timesteps, enabling the action head to operate on predicted outputs while the expensive VLM backbone is called only periodically. We instantiate Latent Bridge on two architecturally distinct VLAs: GR00T-N1.6 (feature-space bridge) and π0.5 (KV-cache bridge), demonstrating that the approach generalizes across VLA designs. Our task-agnostic DAgger training pipeline transfers across benchmarks without modification. Across four LIBERO suites, 24 RoboCasa kitchen tasks, and the ALOHA sim transfer-cube task, Latent Bridge achieves 95-100% performance retention while reducing VLM calls by 50-75%, yielding 1.65-1.73x net per-episode speedup.

Long-tail Internet photo reconstruction

Internet photo collections exhibit an extremely long-tailed distribution: a few famous landmarks are densely photographed and easily reconstructed in 3D, while most real-world sites are represented with sparse, noisy, uneven imagery beyond the capabilities of both classical and learned 3D methods. We believe that tackling this long-tail regime represents one of the next frontiers for 3D foundation models. Although reliable ground-truth 3D supervision from sparse scenes is challenging to acquire, we observe that it can be effectively simulated by sampling sparse subsets from well-reconstructed Internet landmarks. To this end, we introduce MegaDepth-X, a large dataset of 3D reconstructions with clean, dense depth, together with a strategy for sampling sets of training images that mimic camera distributions in long-tail scenes. Finetuning 3D foundation models with these components yields robust reconstructions under extreme sparsity, and also enables more reliable reconstruction in symmetric and repetitive scenes, while preserving generalization to standard, dense 3D benchmark datasets.

BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning

Proximal constraints are fundamental to the stability of the Large Language Model reinforcement learning. While the canonical clipping mechanism in PPO serves as an efficient surrogate for trust regions, we identify a critical bottleneck: fixed bounds strictly constrain the upward update margin of low-probability actions, disproportionately suppressing high-advantage tail strategies and inducing rapid entropy collapse. To address this, we introduce Band-constrained Policy Optimization (BandPO). BandPO replaces canonical clipping with Band, a unified theoretical operator that projects trust regions defined by f-divergences into dynamic, probability-aware clipping intervals. Theoretical analysis confirms that Band effectively resolves this exploration bottleneck. We formulate this mapping as a convex optimization problem, guaranteeing a globally optimal numerical solution while deriving closed-form solutions for specific divergences. Extensive experiments across diverse models and datasets demonstrate that BandPO consistently outperforms canonical clipping and Clip-Higher, while robustly mitigating entropy collapse.

Autonomous Chain-of-Thought Distillation for Graph-Based Fraud Detection

Graph-based fraud detection on text-attributed graphs (TAGs) requires jointly modeling rich textual semantics and relational dependencies. However, existing LLM-enhanced GNN approaches are constrained by predefined prompting and decoupled training pipelines, limiting reasoning autonomy and weakening semantic-structural alignment. We propose FraudCoT, a unified framework that advances TAG-based fraud detection through autonomous, graph-aware chain-of-thought (CoT) reasoning and scalable LLM-GNN co-training. To address the limitations of predefined prompts, we introduce a fraud-aware selective CoT distillation mechanism that generates diverse reasoning paths and enhances semantic-structural understanding. These distilled CoTs are integrated into node texts, providing GNNs with enriched, multi-hop semantic and structural cues for fraud detection. Furthermore, we develop an efficient asymmetric co-training strategy that enables end-to-end optimization while significantly reducing the computational cost of naive joint training. Extensive experiments on public and industrial benchmarks demonstrate that FraudCoT achieves up to 8.8% AUPRC improvement over state-of-the-art methods and delivers up to 1,066x speedup in training throughput, substantially advancing both detection performance and efficiency.

Understanding Pure Textual Reasoning for Blind Image Quality Assessment

Textual reasoning has recently been widely adopted in Blind Image Quality Assessment (BIQA). However, it remains unclear how textual information contributes to quality prediction and to what extent text can represent the score-related image contents. This work addresses these questions from an information-flow perspective by comparing existing BIQA models with three paradigms designed to learn the image-text-score relationship: Chain-of-Thought, Self-Consistency, and Autoencoder. Our experiments show that the score prediction performance of the existing model significantly drops when only textual information is used for prediction. Whereas the Chain-of-Thought paradigm introduces little improvement in BIQA performance, the Self-Consistency paradigm significantly reduces the gap between image- and text-conditioned predictions, narrowing the PLCC/SRCC difference to 0.02/0.03. The Autoencoder-like paradigm is less effective in closing the image-text gap, yet it reveals a direction for further optimization. These findings provide insights into how to improve the textual reasoning for BIQA and high-level vision tasks.

PathFound: An Agentic Multimodal Model Activating Evidence-seeking Pathological Diagnosis

Recent pathological foundation models have substantially advanced visual representation learning and multimodal interaction. However, most models still rely on a static inference paradigm in which whole-slide images are processed once to produce predictions, without reassessment or targeted evidence acquisition under ambiguous diagnoses. This contrasts with clinical diagnostic workflows that refine hypotheses through repeated slide observations and further examination requests. We propose PathFound, an agentic multimodal model designed to support evidence-seeking inference in pathological diagnosis. PathFound integrates the power of pathological visual foundation models, vision-language models, and reasoning models trained with reinforcement learning to perform proactive information acquisition and diagnosis refinement by progressing through the initial diagnosis, evidence-seeking, and final decision stages. Across several large multimodal models, adopting this strategy consistently improves diagnostic accuracy, indicating the effectiveness of evidence-seeking workflows in computational pathology. Among these models, PathFound achieves state-of-the-art diagnostic performance across diverse clinical scenarios and demonstrates strong potential to discover subtle details, such as nuclear features and local invasions.

Guiding Perception-Reasoning Closer to Human in Blind Image Quality Assessment

Humans assess image quality through a perception-reasoning cascade, integrating sensory cues with implicit reasoning to form self-consistent judgments. In this work, we investigate how a model can acquire both human-like and self-consistent reasoning capability for blind image quality assessment (BIQA). We first collect human evaluation data that capture several aspects of human perception-reasoning pipeline. Then, we adopt reinforcement learning, using human annotations as reward signals to guide the model toward human-like perception and reasoning. To enable the model to internalize self-consistent reasoning capability, we design a reward that drives the model to infer the image quality purely from self-generated descriptions. Empirically, our approach achieves score prediction performance comparable to state-of-the-art BIQA systems under general metrics, including Pearson and Spearman correlation coefficients. In addition to the rating score, we assess human-model alignment using ROUGE-1 to measure the similarity between model-generated and human perception-reasoning chains. On over 1,000 human-annotated samples, our model reaches a ROUGE-1 score of 0.512 (cf. 0.443 for baseline), indicating substantial coverage of human explanations and marking a step toward human-like interpretable reasoning in BIQA.

Investigate the Low-level Visual Perception in Vision-Language based Image Quality Assessment

Recent advances in Image Quality Assessment (IQA) have leveraged Multi-modal Large Language Models (MLLMs) to generate descriptive explanations. However, despite their strong visual perception modules, these models often fail to reliably detect basic low-level distortions such as blur, noise, and compression, and may produce inconsistent evaluations across repeated inferences. This raises an essential question: do MLLM-based IQA systems truly perceive the visual features that matter? To examine this issue, we introduce a low-level distortion perception task that requires models to classify specific distortion types. Our component-wise analysis shows that although MLLMs are structurally capable of representing such distortions, they tend to overfit training templates, leading to biases in quality scoring. As a result, critical low-level features are weakened or lost during the vision-language alignment transfer stage. Furthermore, by computing the semantic distance between visual features and corresponding semantic tokens before and after component-wise fine-tuning, we show that improving the alignment of the vision encoder dramatically enhances distortion recognition accuracy, increasing it from 14.92% to 84.43%. Overall, these findings indicate that incorporating dedicated constraints on the vision encoder can strengthen text-explainable visual representations and enable MLLM-based pipelines to produce more coherent and interpretable reasoning in vision-centric tasks.