VideoKR supplies 315K knowledge-intensive video reasoning examples and a dedicated benchmark, with experiments indicating post-training gains on reasoning tasks that require both video content and external knowledge.
Eagle 2.5: Boosting long-context post-training for frontier vision-language models
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 2
baseline 2
citation-polarity summary
verdicts
UNVERDICTED 9representative citing papers
BERAG applies Bayesian ensemble weighting of individual documents via token-by-token posterior updates in retrieval-augmented generation, yielding gains on knowledge-based visual QA tasks.
A new multi-frame VQA benchmark on volumetric MRI demonstrates that bounding-box supervised fine-tuning improves spatial grounding in VLMs over zero-shot baselines.
Replacing Gaussian noise with a temporally grounded prior from recent actions straightens flow-matching paths and improves success rates in robotic manipulation and prior-space RL.
Gaze Attention groups visual embeddings into selectable regions and dynamically restricts attention to task-relevant ones, matching dense baselines with up to 90% fewer visual KV entries via added context tokens.
OFlow unifies temporal foresight and object-aware reasoning inside a shared latent space via flow matching to improve VLA robustness in robotic manipulation under distribution shifts.
XComp reaches extreme video compression (one token per selective frame) via learnable progressive token compression and question-conditioned frame selection, lifting LVBench accuracy from 42.9 percent to 46.2 percent after tuning on 2.5 percent of standard data.
ThinkAct introduces reinforced visual latent planning in a dual VLA system to enable better long-horizon reasoning and adaptation for embodied tasks.
RLDX-1 outperforms frontier VLAs such as π0.5 and GR00T N1.6 on dexterous manipulation benchmarks, reaching 86.8% success on ALLEX humanoid tasks versus around 40% for the baselines.
citing papers explorer
-
VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding
VideoKR supplies 315K knowledge-intensive video reasoning examples and a dedicated benchmark, with experiments indicating post-training gains on reasoning tasks that require both video content and external knowledge.
-
BERAG: Bayesian Ensemble Retrieval-Augmented Generation for Knowledge-based Visual Question Answering
BERAG applies Bayesian ensemble weighting of individual documents via token-by-token posterior updates in retrieval-augmented generation, yielding gains on knowledge-based visual QA tasks.
-
Beyond a Single Frame: Multi-Frame Spatially Grounded Reasoning Across Volumetric MRI
A new multi-frame VQA benchmark on volumetric MRI demonstrates that bounding-box supervised fine-tuning improves spatial grounding in VLMs over zero-shot baselines.
-
WarmPrior: Straightening Flow-Matching Policies with Temporal Priors
Replacing Gaussian noise with a temporally grounded prior from recent actions straightens flow-matching paths and improves success rates in robotic manipulation and prior-space RL.
-
Learning to See What You Need: Gaze Attention for Multimodal Large Language Models
Gaze Attention groups visual embeddings into selectable regions and dynamically restricts attention to task-relevant ones, matching dense baselines with up to 90% fewer visual KV entries via added context tokens.
-
OFlow: Injecting Object-Aware Temporal Flow Matching for Robust Robotic Manipulation
OFlow unifies temporal foresight and object-aware reasoning inside a shared latent space via flow matching to improve VLA robustness in robotic manipulation under distribution shifts.
-
One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding
XComp reaches extreme video compression (one token per selective frame) via learnable progressive token compression and question-conditioned frame selection, lifting LVBench accuracy from 42.9 percent to 46.2 percent after tuning on 2.5 percent of standard data.
-
ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning
ThinkAct introduces reinforced visual latent planning in a dual VLA system to enable better long-horizon reasoning and adaptation for embodied tasks.
-
RLDX-1 Technical Report
RLDX-1 outperforms frontier VLAs such as π0.5 and GR00T N1.6 on dexterous manipulation benchmarks, reaching 86.8% success on ALLEX humanoid tasks versus around 40% for the baselines.