Knowledge catalogue
arXiv:2609.36590v1 Announce Type: new Abstract: Self-speculative decoding accelerates large language model (LLM) inference by drafting tokens from the target model itself, but faces a sharp tradeoff b
arXiv:2609.37968v1 Announce Type: new Abstract: Advances in the coding capabilities of LLM agents allow them to inspect and modify their own instructions, tools, and execution procedures. Existing app
Generated with H3: Mock H3 version of the ending to Wargames(83) as a test of a custom node I've been working on w/ both Claude(Opus/Fable) and OAI's Sol/Astra. One click generation using only 4 movie
arXiv:2609.37539v1 Announce Type: new Abstract: Skills equip LLM agents with professional knowledge and guidance to complete long-horizon and complex tasks. Although skills have been widely adopted in
arXiv:2609.37581v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) excel at visual understanding and reasoning but often incur substantial inference costs due to the large number of visua
arXiv:2603.28773v2 Announce Type: replace-cross Abstract: Large language models (LLMs) frequently generate confident yet factually incorrect content when used for language generation (a phenomenon oft
arXiv:2609.37076v1 Announce Type: new Abstract: Large language models trained on vast corpora inherently risk memorizing harmful content that may later re-emerge in their outputs. To mitigate this iss
arXiv:2609.36805v1 Announce Type: new Abstract: Large language model (LLM) agents reuse external memory to guide new tasks, but effective retrieval requires learning which memory sets improve executio
Written by: Robin Grunewald, Supriya Mazumdar, Kelli Vanderlee Introduction Google Threat Intelligence Group (GTIG) examines vulnerability disclosure and exploitation statistics to evaluate the impact
arXiv:2609.36686v1 Announce Type: new Abstract: Identifying the root cause of an anomaly among hundreds of sensors is critical for preventing safety incidents and costly downtime in complex monitored
arXiv:2609.32720v1 Announce Type: new Abstract: Reward models score responses from large language models (LLMs) and guide LLM training toward human preferences. However, reward models can favor superf
arXiv:2609.34245v1 Announce Type: cross Abstract: LLM agents increasingly take privileged, often irreversible structured actions, such as paying an invoice. They assemble each action from action-criti
arXiv:2609.32255v1 Announce Type: cross Abstract: Tool-using LLM agents must decide not only whether additional information is needed, but also which source can resolve the uncertainty. Existing proac
arXiv:2609.35315v1 Announce Type: new Abstract: Large Language Model (LLM)-based agents promise to automate scientific discovery, yet exploring the vast hypothesis space remains costly. Existing princ
arXiv:2604.01601v2 Announce Type: replace Abstract: In-context fine-tuning (IC-Train), training an LLM with labeled examples in-context, is increasingly used in place of standard fine-tuning for domai
arXiv:2609.32805v1 Announce Type: cross Abstract: Long tasks produce more history than an LLM agent can hold in its context, and more than it uses reliably even when the history fits. A growing line o
arXiv:2609.32663v1 Announce Type: new Abstract: The memory usage and decoding latency of LLM inference grow rapidly with context length. To reduce these costs, key-value (KV) cache compression methods
arXiv:2609.34058v1 Announce Type: new Abstract: AI systems often feel brittle and fragmented. A large language model (LLM) may correctly explain a concept but fail to apply it, or follow safety instru
arXiv:2609.33762v1 Announce Type: cross Abstract: LLM agents resend their whole conversation on every turn, and most of it was already processed on the previous turn. Serving systems avoid recomputing
arXiv:2609.35568v1 Announce Type: new Abstract: High-performance kernels underpin efficient accelerator execution but require expert tuning and lengthy manual optimization cycles. LLM coding agents pr
arXiv:2609.34633v1 Announce Type: new Abstract: Long-term memory supports the self-evolution of LLM agents by retaining experience and skills across tasks and enabling their retrieval, reuse, and revi
arXiv:2609.35335v1 Announce Type: new Abstract: Machine learning task type identification is essential for constructing valid ML pipelines, yet in practice it is typically specified manually. We inves
arXiv:2609.33848v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly undertake extreme-long (xlong) horizon tasks, where a single execution can span hours, hundreds of model-
You may think that jev, OpenClaw or TurboQuant are super cool, but actually the coolest LLM invention happened two years ago As we all know, the best source of reliable information about LLMs is YouTu
arXiv:2609.34905v1 Announce Type: new Abstract: Power sampling has emerged as a training-free approach to LLM reasoning, eliciting capabilities comparable to reinforcement learning by sharpening the m
arXiv:2603.09160v2 Announce Type: replace Abstract: Dense image captioning is critical for vision-language pretraining and for text-to-image generation, but scaling expert-quality annotations is prohi
arXiv:2609.34736v1 Announce Type: cross Abstract: Large language model (LLM) routing aims to select the most suitable model for each incoming query. Most existing routers learn this decision directly
Not an LLM, but the ternary findings should carry over, and we hadn't seen Sherry-style 3:4 weights run in a browser before. Disclosure: this is our work at Precisit, everything is MIT. What it is A 7
arXiv:2607.10522v2 Announce Type: replace Abstract: Large language model (LLM) agents are beginning to automate machine learning engineering (MLE) by coupling planning, code execution, debugging, and
arXiv:2609.32792v1 Announce Type: new Abstract: LLM post-training combines supervised fine-tuning (SFT), a mode-covering forward-KL objective, with reinforcement learning (RL), a mode-seeking reverse-
arXiv:2602.05548v4 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR), particularly GRPO, has become the standard for eliciting LLM reasoning. However, its efficien
arXiv:2509.23219v2 Announce Type: replace Abstract: Technical-domain benchmarks constructed from arXiv papers can overlap the same public text used in LLM pretraining. Auditing this risk at training-c
arXiv:2609.30466v1 Announce Type: cross Abstract: Everyday Extended Reality (XR) systems aim to provide context-aware access to the right functionalities at the right time and place, with minimal manu
arXiv:2609.30642v1 Announce Type: cross Abstract: As Large Language Models (LLMs) become integrated into software development workflows, concerns regarding unintentional biases in AI-generated code. A
arXiv:2609.30428v1 Announce Type: cross Abstract: Foundation models provide robots with the ability to interpret natural language and reason about environmental context, yet most language-conditioned
America is starting to be World Model-pilled Heard a crazy stat the other day. Video generation represents around 70% of the share of AI token consumption in China. A combination of short form content
arXiv:2609.30884v1 Announce Type: new Abstract: Large language models rely on KV caching to reduce repeated prefill computation in long context and interactive applications. As lightweight adapters ev
arXiv:2609.31062v1 Announce Type: new Abstract: Patient-facing AI assistants promise valuable support to patients, but incoming queries can pose medical risks. To create guardrails, we work with oncol
arXiv:2609.31551v1 Announce Type: cross Abstract: Disaggregating the two stages, Prefill and Decode, onto separate GPU pools is now a standard optimization for (text-only) LLM serving. However, multim
arXiv:2606.20626v2 Announce Type: replace-cross Abstract: Safety benchmarks for language models are typically evaluated using static paradigms that treat all items as equally informative for all model
arXiv:2609.30986v1 Announce Type: new Abstract: As large language models increasingly mediate information access, factually accurate and independent answers are critical. However, these models can exh
arXiv:2609.30954v1 Announce Type: new Abstract: Large language models operating in multilingual contexts must resolve target response languages early in generation, yet the causal circuitry governing
arXiv:2609.30547v1 Announce Type: new Abstract: Audience sizing is a critical component of digital marketing. It enables precise resource allocation, campaign planning, and performance optimization. T
arXiv:2609.31282v1 Announce Type: cross Abstract: This paper proposes a blockchain-backed agentic security framework designed to safeguard the complete software development lifecycle (SDLC) while also
arXiv:2609.30861v1 Announce Type: new Abstract: Language-model agents increasingly improve by converting execution experience into reusable external skills. Yet repeated skill updates form a learning
arXiv:2609.31291v1 Announce Type: cross Abstract: Large vocabularies make output heads a substantial inference cost in small language models. We propose softmax reparameterization, a post-training met
arXiv:2609.31571v1 Announce Type: new Abstract: Many LLM training and inference methods, including RL and test-time scaling, depend on repeated sampling, but benefit only when the responses meaningful
arXiv:2609.30614v1 Announce Type: cross Abstract: Dataspace connectors decide whether a transfer may occur, not what the transferred value contains, tolerable for contracted applications, not for LLM
arXiv:2609.30854v1 Announce Type: cross Abstract: Autoregressive LLM inference at long context is bounded by memory bandwidth, not arithmetic throughput, and the binding resource shifts from model wei
arXiv:2609.31603v1 Announce Type: cross Abstract: Large language models (LLMs) implicitly infer attributes of their users and adapt their behavior accordingly, yet these beliefs remain difficult to in
arXiv:2609.30883v1 Announce Type: cross Abstract: AI agents built on a few shared models increasingly act for many people. A shared forecast about others can align their choices and change how scarce
arXiv:2609.30719v1 Announce Type: cross Abstract: Contemporary on-chain artificial intelligence (AI) encounters an intractable Von Neumann memory and latency wall. Storing static floating-point neural
arXiv:2609.31214v1 Announce Type: new Abstract: Estimating the influence of training examples on model behavior is essential for data debugging, valuation, and attribution. Existing influence estimato
A little Ember-1 tl;dr. Seems like a great model! (Was recently asked on a podcast, given $ xx million, what's the best way to develop a frontier LLM today? My recommendation was: start with an existi
Cool paper on catching alignment failures with Jev. The ideas is to ask Jev one generic yes/no question about a model's response, and use its probability as a score. With no extra training, that score
Hello everyone, I made a calculator for the theoretical HW roofline for decoding / prefill based on several parameters (LLM model architecture, quants, GPU, Memory, ..). It still a theoretical bound,
AI grad student here. With all the recent interest in Jev, I thought I would share something I built la few months ago that brings ML models and LLMs together in a different way than Jev does for diff
i don’t get it fully but this looks cool We achieved a breakthrough at BTL. AI models are very linear. They think in one direction at a time, and when they're wrong they scramble and start again. For
arXiv:2609.30205v1 Announce Type: new Abstract: Large language model (LLM)-based clinical assistants are increasingly being integrated into electronic health record (EHR) systems, transforming how cli
arXiv:2609.29014v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent systems can automate alpha factor mining, but their reliance on external APIs limits control over cost, ava