Explore tools, prompts, skills, news and resources related to LLM 第9页.
Prompt works related to LLM 第9页
Latest articles, prompts, use cases and editorial content about LLM 第9页
The paper studies how stale repository instruction files such as AGENTS.md and CLAUDE.md affect LLM-based coding agents. Using three real-world stale instructions, 22 maintenance tasks, and 732 trajectories from two mode...
Researchers propose ROSE, a framework for lifelong knowledge editing in multimodal large language models that restricts parameter updates to the orthogonal complement of previously edited subspaces to reduce interference...
NVIDIA Nemotron 3.5 Super VL, a vision-language model in the Nemotron 3.5 family, is now available in Amazon SageMaker JumpStart. It accepts images, video, and text and generates text, pairing a 120B-parameter hybrid Mix...
AWS announced the availability of Anthropic's Claude Fable 5.2 and Claude Mythos 5.2 on Amazon Bedrock and Claude Platform on AWS. Fable 5.2 is positioned for demanding technical work including coding, math, science...
AWS says Amazon Bedrock Managed Knowledge Base now supports single-shot RAG and retrieval-only requests through AgenticRetrieveStream. By setting maxAgentIteration to 0, applications can return passages without an LLM ca...
FOSCAR is a GPU kernel library that speeds up decode attention over 2-bit and 4-bit quantized KV caches by applying scale and offset through affine folding rather than per-value conversion. It uses bit manipulation and w...
MemoryDojo is a benchmark for tracing how poisoned information propagates through LLM agent memory systems across sessions and measuring its influence on later agent behavior. It comprises 155 multi-session long-horizon...
The paper proposes Intent-Aware Caching (IAC), an online eviction policy for key-value prefix caches in LLM serving systems. It classifies incoming requests by user intent, learns lightweight reuse statistics from recent...
The paper proposes Head-Adaptive Sparse Attention (HASA), a training-free sparse attention framework for LLMs that adapts selection resolution along feature and sequence dimensions. It uses each pretrained head's qu...
Baidu announced ERNIE Evolve, an automated research system that proposes research directions, edits AI training and inference code, runs experiments, and keeps changes only after passing a hidden evaluator and reviewer....
Google announced TPU 8i Max and TPU 8tx as new system configurations within its eighth-generation TPU lineup. TPU 8i Max packages two TPU 8i chips to double compute, SRAM and HBM bandwidth in the same rack footprint for...
Researchers propose QGPM, a training-free method that reshapes rotary position embeddings using query relevance derived from the model's own attention heads. It builds a broad relevance map for lower layers and a sh...
V-STORM is a framework that converts videos into Spatio-Temporal Scene Graphs and derives Grounded Chain of Thought annotations, linking each reasoning step to explicit spatio-temporal evidence. It includes a 260K-sample...
LEMMO is a large electromagnetic model for instruction-driven recognition and description of long raw IQ recordings. It combines a linear-attention EM encoder with anti-aliased temporal resampling to process up to eight...
Researchers introduce a counterfactual audit that reassigns category definitions among output labels to test whether LLM annotations follow supplied definitions or preserve a dataset's original label mapping. Across...
The paper examines watermark-based data-use auditing for LLMs from an adversarial angle, positing a non-compliant provider that trains on unauthorized data and tries to hide it from auditors. It proposes Logit Laundering...
0sec Labs has released 0, an open-source AI security harness for vulnerability investigations, code review, pentesting, reverse engineering and fix generation. It is a research preview under MIT OR Apache-2.0, runs throu...
The paper applies weight-space programming to a robot foundation policy: a language model reads the policy's weights and edits token-embedding rows using a CPU workspace and budgeted simulator feedback, with no grad...
The paper introduces OpenMeter, a schema-agnostic multi-agent system that translates natural-language queries over industrial smart meter data into executable code and human-readable insights. It targets utility staff wi...