b11304
llama: properly handle KV on training (#28520) llama: properly handle KV on training improve Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/51644581 macOS/
Knowledge catalogue
llama: properly handle KV on training (#28520) llama: properly handle KV on training improve Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/51644581 macOS/
test-llama-archs : toggle causal_attn to catch graph shape changes (#29724) After the device decode, flip causal_attn off, decode n_ubatch/2 then n_ubatch tokens. Both have the same node count, so a s
'AREX-2 is a 27B-parameter long-horizon agent model from the Beijing Academy of Artificial Intelligence (BAAI). It learns to improve a solution over multiple test-time rounds: propose, measure, reflec
arXiv:2609.36738v1 Announce Type: cross Abstract: Optimizer momentum is usually stored as a parameter-sized moving average of past gradients, which makes history costly and fixes each past signal in t
arXiv:2609.37041v1 Announce Type: cross Abstract: Self-Distillation Fine-Tuning (SDFT) enables a language model to act as its own teacher: by conditioning on a demonstration, the model produces an imp
arXiv:2609.37400v1 Announce Type: new Abstract: Generating realistic 3D dance from music is a challenging task that requires accurate synchronization with musical rhythms while capturing the spatial c
arXiv:2609.36920v1 Announce Type: new Abstract: Comprehensive evaluations of automatic speech recognition (ASR) for Iberian languages remain limited, and low-resource languages, biases, and efficiency
Building a local voice chat pipeline: Struggling with fast, natural PT-BR conversation models I'm currently trying to build a local AI voice chat system that can use tools via an LLM. I'm testing tw
arXiv:2609.36097v1 Announce Type: cross Abstract: Using predictive models to explain cognition requires more than accurate behavioral predictions. Input ablations offer an appealing route: remove info
arXiv:2609.36628v1 Announce Type: new Abstract: Vision-Language Models (VLMs) can generate rich video captions, yet often misidentify which person performs an action or which limb is involved, particu
arXiv:2609.37066v1 Announce Type: cross Abstract: Post-training is central to mathematical reasoning in modern large language models (LLMs), but endpoint pass@1 alone underidentifies what has changed.
arXiv:2609.37905v1 Announce Type: cross Abstract: Click-Through Rate prediction, a core task in recommendation and advertising systems, relies on modeling interactions among sparse categorical feature
arXiv:2609.36598v1 Announce Type: new Abstract: A video can exhibit convincing motion and photorealism yet fail immediately when visual text collapses. Unlike generic scene content, visual text is unf
arXiv:2609.38019v1 Announce Type: new Abstract: We present RGOR (Reference-Grounded Oral Refinement), an audio-driven lip-sync framework that renders the mouth of the specific person being dubbed rath
arXiv:2609.37027v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) is a widely used approach to parameter-efficient fine-tuning (PEFT), yet a performance gap can remain relative to full fine-t
arXiv:2602.11678v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have shown remarkable progress in visual understanding, yet they suffer from a critical limitation: structu
arXiv:2609.37377v1 Announce Type: new Abstract: On-policy distillation (OPD) trains students using teacher feedback on their own sampled responses, yet how prompt choice shapes transfer across teacher
arXiv:2609.35841v1 Announce Type: cross Abstract: Mutation testing evaluates test-suite adequacy by injecting synthetic faults into program code. However, traditional rule-based tools often generate l
arXiv:2609.36888v1 Announce Type: new Abstract: Mixed human-LLM documents require locating authorship transitions from detector scores whose reliability varies across text units. Existing weighted mea
arXiv:2609.35875v1 Announce Type: new Abstract: Multi-agent debate (MAD) reportedly improves reasoning and factuality over single-model inference, but prior work treats agents as symmetric peers, leav
arXiv:2609.35831v1 Announce Type: new Abstract: Modern large language models now support context windows of more than one million tokens, which has raised the question of whether retrieval-augmented g
arXiv:2609.37713v1 Announce Type: new Abstract: Existing product matching benchmarks primarily contain English-language product data and are often dominated by a single product category, such as elect
arXiv:2609.37993v1 Announce Type: cross Abstract: The BITEM team entered both subtasks of the NTCIR-19 R2C2 task with a single agentic pipeline, in which a model searches, reads and records evidence o
arXiv:2512.07011v2 Announce Type: replace-cross Abstract: Modern large language models increasingly require long contexts for reasoning and multi-document tasks, but attention's quadratic complexity c
arXiv:2603.08249v2 Announce Type: replace-cross Abstract: Audiovisual speech recognition (AVSR) combines acoustic and visual cues to improve transcription robustness under challenging conditions but r
arXiv:2609.38140v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE), popularized by large language models, is a promising paradigm for scaling visual generative models. However, conventional to
arXiv:2609.36660v1 Announce Type: new Abstract: We study federated learning (FL) with adversarial clients, where the goal is to minimize the average loss of the honest (non-adversarial) clients withou
arXiv:2609.36828v1 Announce Type: new Abstract: Post-training quantization (PTQ) lowers deployment cost for multimodal large language models, but calibration typically reconstructs fixed sequences wit
arXiv:2609.35795v1 Announce Type: cross Abstract: Asthma deterioration forecasting must remain reli- able when patient populations, sensor ecosystems, and available modalities change across cohorts. E
arXiv:2609.36721v1 Announce Type: new Abstract: Fixed-budget adaptation from heterogeneous data sources requires deciding not only how much data to use, but how much exposure each source receives. Siz
arXiv:2609.36730v1 Announce Type: new Abstract: Agents increasingly build on code written by other agents, and they reimplement rather than reuse, growing the codebases later agents must work in. To m
arXiv:2609.36726v1 Announce Type: new Abstract: Can a scientific agent distinguish a law it inferred from evidence from one it merely recognizes? We introduce Synthetic Universes, a controlled benchma
arXiv:2609.36914v1 Announce Type: new Abstract: Post-training has been shown to significantly improve language models' performance on tasks with verifiable outcomes, including mathematical reasoning,
arXiv:2609.35809v1 Announce Type: cross Abstract: The rapid advancement of generative AI raises concerns about the misuse of Multimodal LLMs (MLLMs) for large-scale disinformation campaigns on social
arXiv:2609.35970v1 Announce Type: cross Abstract: Large language models are able to solve tasks whose answers depend on not only individual input tokens, but also on relations among them. How is such
arXiv:2609.36776v1 Announce Type: new Abstract: Emotional Video Captioning aims to generate factually accurate and emotionally empathetic descriptions. While recent methods have recognized the importa
arXiv:2504.14015v2 Announce Type: replace-cross Abstract: We introduce 'causal pieces', a novel concept for analysing spiking neural networks (SNNs), inspired by 'linear pieces' used to study expressi
arXiv:2609.36986v1 Announce Type: new Abstract: Federated LoRA fine-tuning enables parameter-efficient adaptation of pre-trained models without sharing private data, but suffers from two fundamental m
arXiv:2609.36453v1 Announce Type: cross Abstract: Multivariate time series forecasting (MTSF) is critical across many real-world domains. Existing deep learning approaches fall into two paradigms with
arXiv:2609.38093v1 Announce Type: new Abstract: Risk aversion in resources could prevent misaligned AI agents from causing catastrophic harm. Misaligned but risk-averse agents would tend to favor safe
arXiv:2609.35909v1 Announce Type: cross Abstract: Autonomous LLM agents turn vulnerability discovery into a repository-scale search: they generate many vulnerability hypotheses but can verify only a s
arXiv:2609.36308v1 Announce Type: new Abstract: Reinforcement learning has helped AI agents solve increasingly difficult tasks, but high rewards do not always reflect the work users intended. In recen
arXiv:2609.36615v1 Announce Type: cross Abstract: Physics-informed neural networks (PINNs) solve partial differential equations (PDEs) by incorporating governing physical laws into the training loss.
arXiv:2609.36218v1 Announce Type: cross Abstract: Large language models are increasingly evaluated in specialized domains such as law, medicine, software engineering, and cybersecurity, yet film remai
arXiv:2609.35883v1 Announce Type: cross Abstract: Genome foundation models are growing into sparse mixture-of-experts (MoE) networks whose expert weights no longer fit on the machines that hold the se
arXiv:2609.36752v1 Announce Type: new Abstract: Circuit design is a complex and iterative process that requires expertise in electronic engineering. It involves selecting components while meeting perf
arXiv:2609.36495v1 Announce Type: new Abstract: Forward kinetostatics of spatial tendon-driven continuum robots typically requires a nonlinear equilibrium solve for each actuation input. This paper de
Welcome to the second Cloud CISO Perspectives for September 2026. Today, Alicja Cade and Nick Godfrey, senior directors, Office of the CISO, share their guidance for cybersecurity startups on how to w
arXiv:2609.36777v1 Announce Type: new Abstract: Frontier coding agents can now write and execute code that authors 3D environments, but whether they reliably understand 3D structure and precisely cont
arXiv:2609.32192v2 Announce Type: replace Abstract: Multi-agent workflows require task-relevant information to be shared across agents, while irrelevant, stale, unverified, or incompatible information
arXiv:2609.37371v1 Announce Type: cross Abstract: Model adaptation is typically governed by a fixed recipe, even though different update programs can produce substantially different behavioral outcome
arXiv:2609.37405v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for software engineering tasks that require understanding existing source code, including behavior
arXiv:2609.37807v1 Announce Type: new Abstract: Studying how fine-tuning shapes refusal and noncompliance behaviour requires identifying training examples that refuse, evade or otherwise fail to fulfi
arXiv:2609.37567v1 Announce Type: cross Abstract: Driven by the rapid advancement of large language models (LLMs), LLM-based multi-agent systems (MAS) have emerged as a powerful paradigm for collabora
arXiv:2609.35814v1 Announce Type: cross Abstract: As browser-use agents improve, benchmarks keep pace by collecting new tasks, websites, and applications, often making tasks longer or more novel. This
arXiv:2609.37743v1 Announce Type: new Abstract: LLM agents performing long-horizon tasks accumulate tool results that later steps may need. Passing the full history to every invocation is costly even
arXiv:2609.38107v1 Announce Type: cross Abstract: Chain-of-thought traces are widely read as records of how models reach their answers, informing debugging, agent auditing, and claims about reasoning.
arXiv:2609.37189v1 Announce Type: new Abstract: We study sparse linear contextual bandits with knapsack constraints under joint reward and consumption corruption. Consumption corruption creates a chal
arXiv:2609.34790v2 Announce Type: replace-cross Abstract: LLM agents operate in persistent collaborative environments involving multiple users, communities, memories, files, and tools. Community bound
arXiv:2609.37841v1 Announce Type: new Abstract: Masked generative models offer parallel token prediction, but accurate parallel sampling must account for dependencies among tokens. When dependencies a