A two-stage framework augments HOI data with dynamic priors and blends pre-trained dynamic motion and static interaction agents via a composer network to enable long-term dynamic human-object interactions with higher success rates and reduced training time.
Learn- ing transferable visual models from natural language super- vision
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 9roles
background 1polarities
background 1representative citing papers
The paper creates FISD, a controlled benchmark for composed image retrieval that removes query ambiguity via generative models, and proposes a multi-round agentic evaluation to assess models in interactive settings.
TRANSPORTER generates videos from VLM logits using optimal transport to interpret model predictions on object attributes, actions, and scenes.
DynProto dynamically builds OOD prototypes from ID-only data via coarse caching and fine clustering of confused samples to improve OOD detection in VLMs, cutting FPR95 by 11.6% on ImageNet benchmarks.
SSL-R1 reformulates visual SSL tasks into verifiable puzzles to supply rewards for RL post-training of MLLMs, yielding gains on multimodal benchmarks without external supervision.
Memorization in Stable Diffusion is driven by the structural duplication of the CLIP <eot> embedding inside <pad> tokens, which causes over-reliance on that vector; simple inference-time masking or token replacement suppresses it without quality loss.
GR3D turns 3D scene geometry into ID-indexed text references, enabling zero-shot MLLM spatial reasoning gains of 9% on VSI-Bench and 12% on MindCube.
Argos is an agentic verifier that adaptively picks scoring functions to evaluate accuracy, localization, and reasoning quality, enabling stronger multimodal RL training for AI agents.
VLM-3R augments VLMs with implicit 3D tokens from monocular video via geometry encoding and 200K+ 3D reconstructive QA pairs, plus a new 138K-pair temporal benchmark, to support spatial and embodied reasoning.
citing papers explorer
-
Dynamic Full-body Motion Agent with Object Interaction via Blending Pre-trained Modular Controllers
A two-stage framework augments HOI data with dynamic priors and blends pre-trained dynamic motion and static interaction agents via a composer network to enable long-term dynamic human-object interactions with higher success rates and reduced training time.
-
A Sanity Check on Composed Image Retrieval
The paper creates FISD, a controlled benchmark for composed image retrieval that removes query ambiguity via generative models, and proposes a multi-round agentic evaluation to assess models in interactive settings.
-
TRANSPORTER: Transferring Visual Semantics from VLM Manifolds
TRANSPORTER generates videos from VLM logits using optimal transport to interpret model predictions on object attributes, actions, and scenes.
-
DynProto: Dynamic Prototype Evolution for Out-of-Distribution Detection
DynProto dynamically builds OOD prototypes from ID-only data via coarse caching and fine clustering of confused samples to improve OOD detection in VLMs, cutting FPR95 by 11.6% on ImageNet benchmarks.
-
SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models
SSL-R1 reformulates visual SSL tasks into verifiable puzzles to supply rewards for RL post-training of MLLMs, yielding gains on multimodal benchmarks without external supervision.
-
Memorization In Stable Diffusion Is Unexpectedly Driven by CLIP Embeddings
Memorization in Stable Diffusion is driven by the structural duplication of the CLIP <eot> embedding inside <pad> tokens, which causes over-reliance on that vector; simple inference-time masking or token replacement suppresses it without quality loss.
-
Boosting MLLM Spatial Reasoning with Geometrically Referenced 3D Scene Representations
GR3D turns 3D scene geometry into ID-indexed text references, enabling zero-shot MLLM spatial reasoning gains of 9% on VSI-Bench and 12% on MindCube.
-
Multimodal Reinforcement Learning with Adaptive Verifier for AI Agents
Argos is an agentic verifier that adaptively picks scoring functions to evaluate accuracy, localization, and reasoning quality, enabling stronger multimodal RL training for AI agents.
-
VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction
VLM-3R augments VLMs with implicit 3D tokens from monocular video via geometry encoding and 200K+ 3D reconstructive QA pairs, plus a new 138K-pair temporal benchmark, to support spatial and embodied reasoning.