Trending Research
Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting
Document image parsing is challenging due to its complexly intertwined elements such as text paragraphs, figures, formulas, and tables.
TradingAgents: Multi-Agents LLM Financial Trading Framework
Significant progress has been made in automated problem-solving using societies of agents powered by large language models (LLMs).
V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
Finally, we show how self-supervised learning can be applied to robotic planning tasks by post-training a latent action-conditioned world model, V-JEPA 2-AC, using less than 62 hours of unlabeled robot videos from the Droid dataset.
Ranked #4 on
Video Question Answering
on TVBench
Towards CausalGPT: A Multi-Agent Approach for Faithful Knowledge Reasoning via Promoting Causal Consistency in LLMs
hcplab-sysu/causal-vlreasoning
•
•
Drawing inspiration from the orchestration of diverse specialized agents collaborating to tackle intricate tasks, we propose a framework named Causal-Consistency Chain-of-Thought (CaCo-CoT) that harnesses multi-agent collaboration to bolster the faithfulness and causality of foundation models, involving a set of reasoners and evaluators.
MEIA: Multimodal Embodied Perception and Interaction in Unknown Environments
To overcome this limitation, we introduce the Multimodal Embodied Interactive Agent (MEIA), capable of translating high-level tasks expressed in natural language into a sequence of executable actions.
MUSt3R: Multi-view Network for Stereo 3D Reconstruction
DUSt3R introduced a novel paradigm in geometric computer vision by proposing a model that can provide dense and unconstrained Stereo 3D Reconstruction of arbitrary image collections with no prior information about camera calibration nor viewpoint poses.
VGGT: Visual Geometry Grounded Transformer
facebookresearch/vggt
•
•
CVPR 2025
We present VGGT, a feed-forward neural network that directly infers all key 3D attributes of a scene, including camera parameters, point maps, depth maps, and 3D point tracks, from one, a few, or hundreds of its views.
Ming-Omni: A Unified Multimodal Model for Perception and Generation
inclusionai/ming
•
•
We propose Ming-Omni, a unified multimodal model capable of processing images, text, audio, and video, while demonstrating strong proficiency in both speech and image generation.
MagCache: Fast Video Generation with Magnitude-Aware Cache
Zehong-Ma/ComfyUI-MagCache
•
•
Existing acceleration techniques for video diffusion models often rely on uniform heuristics or time-embedding variants to skip timesteps and reuse cached features.
R-KV: Redundancy-aware KV Cache Compression for Training-Free Reasoning Models Acceleration
To address this, we propose Redundancy-aware KV Cache Compression for Reasoning models (R-KV), a novel method specifically targeting redundant tokens in reasoning models.
