SphereFlow imputes missing modalities via hyperspherical transport
SphereFlow projects modalities to shared hypersphere for short-range cross-modal flow, achieving state-of-the-art on BraTS MRI imputation and closing 80% of segmentation gap.
15
Organization
huggingface
- Mentions · 7d2
- Mentions · 30d5
- All mentions5
- First seenOct 25, 2026
- Last mentioned6d ago
Timeline
5 articles · newest firstAttention competition predicts context rot in retrieval
Filler tokens maintain accuracy up to 32K tokens in retrieval but rival statements multiply loss by 9-110 across five open models.
15
Entity-replacement responses transfer across questions
Hidden-state reuse removes 45-49% of no-change errors on 0.5-1B Qwen and Llama models for entity-replacement responses.
15
OpenFrontiers benchmark tests LLM scientific rediscovery
The benchmark grades 200 math problems with 110 resolved in 2026 under closed-book, live-web and sandboxed conditions, revealing rare closed-book success.
50
Process rewards improve video editing agents but risk reward hacking
Decaying process rewards yield 45.4% gain on long-horizon fine-cut tasks but mitigate reward hacking in GRPO training.
15
Appears with
- gemma-2-2bai model · 1
- qwenai model · 1
- SphereFlowai model · 1
- grpoai model · 1
- llamaai model · 1
- qwen2.5-1.5bai model · 1
- opsdai model · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.