Introduces the Grounded Personality Reasoning task and MM-OCEAN dataset to show that MLLMs frequently produce correct Big Five personality ratings without grounding them in observable video evidence.
hub Canonical reference
Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks
Canonical reference. 87% of citing Pith papers cite this work as background.
24
Pith papers citing it
Background
87% of classified citations
hub tools
citation-role summary
background 13
baseline 2
citation-polarity summary
representative citing papers
EventPrune prunes 80% of visual tokens in Video-LLMs using event camera motion cues, yielding 1.89x speedup, 52% fewer GFLOPs, and slightly higher accuracy than full-token baselines on first-person dynamic spatial reasoning.
RotateK uses online PCA-based rotation to align token-dependent key channel importance into a shared subspace, enabling accurate head-wise structured pruning and faster decoding in VLMs compared to prior token or channel methods.
RotVLA models latent actions as continuous SO(n) rotations with triplet-frame supervision and flow-matching to reach 98.2% success on LIBERO and 89.6%/88.5% on RoboTwin2.0 using a 1.7B-parameter model.
VLMs show a resolution illusion on UHR Earth observation imagery where higher resolution does not improve micro-target perception; UHR-Micro benchmark and MAP-Agent address this via evidence-centered active inspection.
CaC presents a new spatiotemporal concentrating reward model for video anomalies, built on a novel large-scale dataset and three-stage training with RL and IoU rewards, claiming 25.7% accuracy gains and 11.7% anomaly reduction.
ViSRA boosts MLLM 3D spatial reasoning performance by up to 28.9% on unseen tasks via a plug-and-play video-based agent that extracts explicit spatial cues from expert models without any post-training.
TOC-Bench is a new diagnostic benchmark that reveals major weaknesses in temporal object consistency for Video-LLMs, including event counting, ordering, identity reasoning, and hallucination avoidance.
CoLVR uses latent contrastive objectives with angle-based perturbation and RL trajectory rewards to increase exploratory visual reasoning in MLLMs, delivering 5-8% gains on VSP, Jigsaw, and MMStar benchmarks.
Temporal information in Video-LLMs is encoded well by video-centric encoders but disrupted by standard projectors; time-preserved MLPs plus AoT supervision yield 98.1% accuracy on arrow-of-time and gains on other temporal tasks.
VISAFF is a tuning-free speaker-centered visual affective feature learning framework for emotion recognition in conversation that guides frozen VLMs to active speakers and uses reliability-guided complementation from textual and acoustic modalities to achieve competitive performance.
MindVLA-U1 is the first unified streaming VLA architecture that surpasses human drivers on WOD-E2E planning metrics while matching VA latency and preserving language interfaces.
ToolCUA introduces a trajectory scaling pipeline and staged RL to optimize GUI-tool switching, reaching 46.85% accuracy on OSWorld-MCP for a 66% relative gain over baseline.
SpatialForge synthesizes 10 million spatial QA pairs from in-the-wild 2D images to train VLMs for better depth ordering, layout, and viewpoint-dependent reasoning.
CoWorld-VLA extracts semantic, geometric, dynamic, and trajectory expert tokens from multi-source supervision and feeds them into a diffusion-based hierarchical planner, achieving competitive collision avoidance and trajectory accuracy on the NAVSIM v1 benchmark.
LLaVA-UHD v4 reduces visual-encoding FLOPs by 55.8% for high-resolution images in MLLMs via slice-based encoding plus intra-ViT early compression while matching or exceeding baseline performance on document, OCR, and VQA benchmarks.
Visual latents in MLLMs are systematically silenced by autoregressive training but can be unsilenced at inference via query-guided contrastive alignment followed by a confidence-progression reward.
SLQ adapts frozen MLLMs for multimodal retrieval by appending shared latent queries to text and image tokens and introduces KARR-Bench to test knowledge-aware reasoning retrieval.
HiFi-Inpaint delivers state-of-the-art detail-preserving human-product images by adding Shared Enhancement Attention and Detail-Aware Loss to reference-based inpainting on a new 40K dataset.
Streamo is a streaming video LLM trained end-to-end on the new Streamo-Instruct-465K dataset that unifies multiple real-time video tasks with claimed strong temporal reasoning and generalization.
DeepEyesV2 uses a two-stage cold-start plus reinforcement learning pipeline to produce an agentic multimodal model that adaptively invokes tools and outperforms direct RL on real-world reasoning benchmarks.
OmniRefine introduces alignment-aware chunk refinement via similarity and dynamic programming followed by modality-cooperative token compression, achieving near-baseline accuracy at 44% token retention on WorldSense.
ERASE prunes 85% of vision tokens in Qwen2.5-VL-7B while retaining 89.46% accuracy, outperforming prior methods that retain only 78.1%.
ShellfishNet is a new benchmark of 8,691 images across 32 mollusc taxa for evaluating vision models on real-world underwater ecological monitoring tasks including robustness to degradation.
citing papers explorer
-
Streaming Video Instruction Tuning
Streamo is a streaming video LLM trained end-to-end on the new Streamo-Instruct-465K dataset that unifies multiple real-time video tasks with claimed strong temporal reasoning and generalization.
-
DeepEyesV2: Toward Agentic Multimodal Model
DeepEyesV2 uses a two-stage cold-start plus reinforcement learning pipeline to produce an agentic multimodal model that adaptively invokes tools and outperforms direct RL on real-world reasoning benchmarks.