The top stories in the fields you follow, at 06:00 your time.
Groq is preparing to replace the SRAM in its AI accelerators with 3D-stacked DRAM in its next-generation chips, according to semiconductor industry…
Read moreModel · diffusion-single-file · 1.3M downloads · 328 likes
Agents built on vision language models (VLMs) now compete with learned policies on robot manipulation leaderboards. We ask how far a coding agent can go when it controls a robot instead of a computer, and where it stops. Our system, HexaShell, keeps the harness thin: it only…
Can large language model (LLM) agents deliver expert-level operations research (OR) solutions directly from original client materials, without prior expert reformulation? Existing OR benchmarks typically begin with self-contained descriptions or predefined optimization tasks,…
Hy-Memory-30B-A3B is a compact long-term-memory writer model (~3B active parameters) developed by Tencent Hunyuan to execute the write path inside external memory frameworks. It directly replaces the general-purpose LLM inside Mem0, MemOS, and Hy-Memory (covering Chat, Working,…
Long-output inference in large language models suffers from severe KV cache memory and bandwidth bottlenecks. While KV cache quantization alleviates this issue, low-bit quantization (e.g., 2-bit) severely degrades model accuracy. Recent mixed-precision key-cache quantization…
In long-horizon tool-calling tasks, LLM agents can fail not only because of tool-use errors, but also because of ineffective interaction with users. Yet existing benchmarks largely assume cooperative and behaviorally stable users, leaving the effect of emotional variation on…
Verifiable instruction-following benchmarks emphasize output-constraint satisfaction but can overlook whether responses meaningfully answer the underlying request, creating an evaluation blind spot. We show that frontier models can receive full credit for responses with little…
