🔬Bio-security is an AI Arms Race - Eric Nguyen (CEO, Radical Numerics)
4 min
The Sirens' Song: When Proximal Background Context Overshadows Distant Evidence
DolphinBench: Mapping the Pareto Frontier of Agent Memory
Alibaba Qwen Releases Qwen3.8-Omni-Flash: A 1M-Context Omni-Modal Model Built Around Agentic Audio-Video Understanding and Tool Use
5 min1
On-Demand Attention: Language Models Know When to Recall
DeepSeek-v4.1 Flash: Pushing the Limits of KV Cache Compression
15 min1
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
1
XingChen-AGI/Xing4.0-29B-A4B — new model trending #30 on Hugging Face
7 min1
Fathom: Per-Query Read Depth for Sparse Decoding over Offloaded KV Caches
1
SpectralShift: Effective Context Window Extension of Gated DeltaNet via Spectral Reparameterization
2
Flattening Every Memory Peak in Long-Context Mixture-of-Experts Training
1
yandex/AliceAI-Foundation-80B-A3B-Base — new model trending #30 on Hugging Face
15 min
[AINews] DeepSeek v4.1-Flash: 763B-P8B-D16B novel causal Encoder–Decoder architecture with vision marks the Return of the Whale
15 min1
SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking
2
Agnes-AI/Agnes-3.0-Flash — new model trending #30 on Hugging Face
12 min
SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking
1
ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search
1
DeepSeek AI Released DeepSeek-V4.1-Flash with 1M Context, FP4 KV Cache, and Cross-Layer Attention Reuse
4 min2
ConvMem: Convolutional Memory for Long-Context Reasoning
Learning Length-Extrapolatable Recurrent Models
1
Kalman Delta Networks: Uncertainty-aware Associative Memory
1
PARSER: Read in Parallel, Reason in Depth for Long-Context LLM Agents
1
IFM/K2-Horizon-MoVA-36B-A4B — new model trending #15 on Hugging Face
15 min
unsloth/Qwen3.8-Flash-Next-GGUF — new model trending #21 on Hugging Face
15 min1