Opinions
Opinion: Hugging Face Is Too Important to Fall Into Nvidia’s Hands
Writing in The Register, Tobias Mann argues that Nvidia’s $12.9 billion acquisition of Hugging Face raises significant antitrust concerns because…
Opinions
Analysis: Runway’s Solaris Is a Compelling Demo With an Unproven Deployment Story
Runway introduced Solaris, an “Interface World Model” that generates software interfaces frame-by-frame from user input, operating without traditional design files…
Engineering
Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM
This work challenges the assumption that recurrent linear-attention layers require higher precision than other model components, showing that the Gated…
Engineering
Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning
This paper addresses the memory bottleneck created by large key-value caches during extended LLM reasoning by proposing Random Attention, which…
Engineering
Hardware-Aware FP4 FlashAttention-4
This work tackles a performance bottleneck in attention computation on Blackwell GPUs’ 4-bit floating-point tensor cores, where softmax conversion and…
Engineering
DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training
This paper addresses the difficulty of assigning credit across long, multi-step agent trajectories during reinforcement learning, where sparse end-of-episode rewards…
Engineering
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
This paper addresses the scarcity of executable environments needed to train terminal-based coding agents by reconstructing usable environments directly from…
Engineering
LatentPress: Context Compression Beyond Text and Vision
This paper addresses the inefficiency of storing and processing long conversational histories and documents by introducing a machine-facing compression interface…
Engineering
Rethinking On-Policy Distillation of Large Language Models II: One Training Example
This paper investigates on-policy distillation (OPD) by studying what happens when training uses minimal data, down to a single query,…
Engineering
Unlocking Lossless Speedups in LLMs via Discrete Diffusion
This paper addresses the slow, strictly sequential token generation inherent to autoregressive language models by introducing diffusion-augmented LLMs that define…
Engineering
Compile by Training: Turning Natural-Language Specifications into Local Neural Functions
This paper addresses text-transformation tasks that are conceptually simple to describe but hard to implement with traditional rule-based code, while…
Engineering
The Natural Language Interaction Protocol and Standard for AI Agents
This paper addresses the lack of standardized interoperability between AI agents built on different frameworks and deployed across organizations. It…