DeltaWAM: Delta World Action Models for Bimanual Manipulation
Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation
Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
1
Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling
[AINews] DeepSeek v4.1-Flash: 763B-P8B-D16B novel causal Encoder–Decoder architecture with vision marks the Return of the Whale
15 min1
Attention Quantization for Tabular Foundation Models
1
New Deepseek model V4.1-Flash cuts memory needs for AI agents
4 min1
TRACE: Trajectory-robust Admission with Evidence Ordering for Efficient GUI Agents
Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs
Grouped Value Attention: Efficient KV Caching via On-Demand Key Reconstruction
Signed Rescue Routing: Harm-Aware Cascades for Efficient LLM Inference
1
ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding
