b10375
chat : tighten bare function parsing for Qwen models (#26793) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64)
Knowledge catalogue
chat : tighten bare function parsing for Qwen models (#26793) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64)
common: Add CLI > ENV > models-presets > INI precedence CLI flags have the highest precedence ENV vars have the second-highest precedence System and User configs have the lowest precedence Linux/BSD/M
arXiv:2606.08348v2 Announce Type: replace Abstract: LLM agents increasingly rely on prompts, tools, memory, SOPs, skills, and harness feedback, yet current self-evolution pipelines often update these
arXiv:2509.05624v3 Announce Type: replace-cross Abstract: How much information about an agent's underlying values can be recovered from its observable behavior? This question matters for any approach
arXiv:2608.10532v1 Announce Type: cross Abstract: Static load balancers cannot mitigate a backend that is degraded rather than down: round-robin and least-connections keep routing traffic to a server
arXiv:2608.10891v1 Announce Type: new Abstract: Time series forecasting in privacy-sensitive domains often requires training models on released data rather than original observations. Synthetic time s
arXiv:2608.10798v1 Announce Type: cross Abstract: Most image colorization systems operate in Lab space by predicting chroma (ab) while preserving an input-derived luminance channel (L). While effectiv
.@BharatKChandar, @RuyuChen and I just released an updated version of our paper 'Canaries in the Coal Mine?' The headline is that we still don't see any widespread job displacement due to AI, but the
arXiv:2608.10204v1 Announce Type: new Abstract: Safe reinforcement learning maximizes reward subject to safety constraints. For Constrained Markov Decision Processes, the linear-programming view over
arXiv:2608.10804v1 Announce Type: cross Abstract: Deep neural networks excel in various tasks but struggle to generalize across evolving data distributions, leading to significant performance degradat
arXiv:2608.10680v1 Announce Type: new Abstract: Visible-infrared object detection relies on complementary RGB and thermal cues, but its performance is often degraded by cross-modal spatial misalignmen
arXiv:2608.10690v1 Announce Type: new Abstract: Pretraining corpus composition shapes LLM capabilities, but it often remains hidden even when model weights are released. Prior work has inferred corpus
arXiv:2608.11074v1 Announce Type: new Abstract: Evaluating detailed image captions from Vision-Language Models (VLMs) requires going beyond surface-level semantic similarity. Reference-based metrics (
arXiv:2608.10677v1 Announce Type: new Abstract: Professionals across medicine, engineering, finance, manufacturing, and the sciences often make consequential decisions from charts. Existing chart benc
arXiv:2608.10090v1 Announce Type: new Abstract: Large language models (LLMs) have advanced code generation, where executable feedback provides a more reliable learning signal than textual imitation al
arXiv:2608.09949v1 Announce Type: new Abstract: This study evaluates the application of Large Language Models (LLMs) in complex biological systems, evolving from data analysis to autonomous, AI-guided
North Micro Vision Instruct is a 2.4B-parameter open-weight vision-language model with native-resolution image support, released under the Apache 2.0 license. It is designed as a compact foundation fo
arXiv:2608.10915v1 Announce Type: new Abstract: After an older adult misses a medication dose, a software agent can send another reminder and an embodied agent can bring the medication. Yet neither ex
arXiv:2608.10765v1 Announce Type: new Abstract: Recognizing human behavior across levels of abstraction, from atomic actions to long-horizon intentions, requires data annotated along a semantic hierar
arXiv:2604.01418v2 Announce Type: replace Abstract: Thousands of diverse benchmarks have been developed to measure the quality of large language models (LLMs). Yet prior work has demonstrated that LLM
arXiv:2608.10296v1 Announce Type: new Abstract: One might imagine that architectural variations within the dense transformer paradigm have a limited effect on accuracy. However, we demonstrate that th
arXiv:2608.10644v1 Announce Type: new Abstract: Extraction produces candidate entities and relationships; writing them into a graph is where identity is decided, and identity decisions are destructive
arXiv:2608.10010v1 Announce Type: new Abstract: Low-precision datatypes reduce language-model cost, but most formats optimize scalar fidelity while leaving the arithmetic induced by their products unc
arXiv:2608.11154v1 Announce Type: new Abstract: Detecting or attributing a supply-chain disruption is not the same as selecting the intervention that maximizes recoverable net value. We present Critic
arXiv:2608.10567v1 Announce Type: new Abstract: Analytic dashboards combine coordinated views and interactions for data exploration and decision-making. Recent models can generate them from data and n
arXiv:2608.10096v1 Announce Type: cross Abstract: Modern data science increasingly gives rise to hypothesis-testing problems that are not naturally formulated in terms of parameters within prespecifie
Since lot's of people were sceptical or whatever, heres how to uncensor / jailbreak V4 flash and proof. No it is not lead on whatever, first prompt, first try, every time. Put this in System message:
DeepSeek V4 Pro 0813 (on OpenRouter) The latest DeepSeek Pro model is now available, via API only. I had to link to OpenRouter because DeepSeek don't have any obvious announcement page for their new m
arXiv:2608.10595v1 Announce Type: cross Abstract: Proteolysis-targeting chimeras (PROTACs) induce protein degradation by recruiting a target protein to an E3 ubiquitin ligase, making degradation a joi
arXiv:2608.11020v1 Announce Type: new Abstract: We systematically investigate finite-difference (FD) derivative computation in Physics-Informed Neural Networks (PINNs) as an alternative to automatic d
arXiv:2608.10850v1 Announce Type: new Abstract: We study continual pre-training (CPT) as a mechanism for adapting general-purpose large language models to specialized domains: mathematics, instruction
arXiv:2608.10636v1 Announce Type: cross Abstract: Visual document retrieval (VDR) is dominated by multi-billion-parameter models that are slow to index at full corpus scale and expensive to serve. Pri
arXiv:2608.10008v1 Announce Type: cross Abstract: LLM recommenders for top-K item suggestion regularly emit titles outside the target catalog. Prior audits measure this as a binary out-of-domain rate;
arXiv:2512.22525v2 Announce Type: replace Abstract: Recently unified generation and editing models have achieved remarkable success with their impressive performance. These models rely mainly on text
arXiv:2608.10413v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for end-to-end autonomous driving by enabling unified reasoning across
arXiv:2608.10366v1 Announce Type: new Abstract: Real-world data science involves long-horizon workflows that span data wrangling, exploration, modeling, visualization, and validation, and require coor
arXiv:2608.10796v1 Announce Type: new Abstract: Understanding both expressed and evoked emotions is critical for multimodal large language models (MLLMs) to achieve comprehensive affect-aware interact
arXiv:2608.10206v1 Announce Type: new Abstract: Detecting phonemes from children's speech has historically been difficult due to the scarcity of training data, and unique characteristics of children's
arXiv:2608.10357v1 Announce Type: cross Abstract: Long-horizon tool-using agents must reason over user goals, domain policies, tool calls, simulator state, and delayed verifiable rewards. Reinforcemen
arXiv:2608.10679v1 Announce Type: cross Abstract: Enterprise question answering is framed as retrieving internal documents and generating grounded answers. Routine enterprise records, however, are wor
Everyone else is talking about building ASI to like monopolize b2b saas and Elon is talking about building a kardashev II sentient sun Media It’s always funny how people in SF twitter bubble will say
arXiv:2608.10954v1 Announce Type: cross Abstract: While Multimodal Large Language Models (MLLMs) demonstrate impressive performance in benign scenarios, their cognitive reliability deteriorates signif
arXiv:2608.10499v1 Announce Type: cross Abstract: Personalized Federated Reinforcement Learning (PFRL) takes a decentralized approach to storing and accessing information based on past experiences whi
arXiv:2507.21606v2 Announce Type: replace Abstract: The success of visual tracking has been largely driven by datasets with manual box annotations. However, these box annotations require tremendous hu
arXiv:2608.10764v1 Announce Type: new Abstract: Counterfactual video understanding evaluates whether models grasp physical and commonsense regularities. However, existing multiple-choice question (MCQ
arXiv:2608.10916v1 Announce Type: cross Abstract: Autoformalisation (AF) systems map natural language reasoning steps into formal statements in a proof assistant such as Lean. We consider how to asses
arXiv:2608.10805v1 Announce Type: cross Abstract: Wavelet convolution (WTConv) has emerged as an increasingly popular drop-in replacement for standard convolutions, expanding a network's receptive fie
arXiv:2608.10860v1 Announce Type: cross Abstract: World-action models (WAMs) predict the future to act better, but nearly all of them predict only RGB latents, trained purely for pixel reconstruction,
arXiv:2608.10396v1 Announce Type: new Abstract: Transforming table-form documents into machine-processable records requires recovering not only their visible content but also the multilevel structure
Four small architecture decisions can cost up to 47% of a model's long-context performance. New research from Ai2, Carnegie Mellon, and the University of Washington isolates them. Normalization, GQA,
From #22 to #4 on Legal Research Bench! Solid progress for Qwen3.8-Max. Thanks for highlighting~✨ Qwen 3.8 Max nearly doubled its score on Legal Research Bench in under three months, climbing from #22
arXiv:2608.10502v1 Announce Type: new Abstract: Persistent memory lets language-model agents reuse information across sessions, but it also makes errors durable: a poisoned, stale, or misattributed re
arXiv:2608.10444v1 Announce Type: cross Abstract: Large language models (LLMs) have made substantial progress on reasoning tasks that require increasingly long and complex inferential chains. This pro
Enterprise content is no longer just something people read. AI apps and agents are only as useful as the information they can understand, yet much of the world’s enterprise knowledge is locked in docu
Link to the article: KV Cache Quantization on Gemma 4 31B: Non-QAT vs QAT KLD benchmarks with BeeLlama.cpp v0.4.3, fork of llama.cpp with more KV cache quantization options, comparing Gemma Q4_0 non-Q
arXiv:2608.10494v1 Announce Type: new Abstract: Earth observation (EO) agents construct scientifically valid tool workflows and ground their conclusions in current geospatial evidence. This is challen
arXiv:2608.10426v1 Announce Type: new Abstract: Open-vocabulary remote sensing segmentation has recently emerged as a promising paradigm that enables pixel-level recognition of arbitrary categories sp
arXiv:2608.10886v1 Announce Type: new Abstract: Robots operating in human environments need memories that capture not only what objects exist and where, but also how people use them over time and how
give 4.6 a try and let us know how it goes. your feedback is a big part of why the model gets better with each iteration. SpaceXAI's Grok 4.6 scores 61 on the Artificial Analysis Intelligence Index, j
arXiv:2509.13211v4 Announce Type: replace Abstract: The ability to learn continuously over time remains a major challenge for modern machine learning systems, even in the era of Foundation Models. Whi