Scale Weight Decay and Train Better
arXiv:2607.23777v1 Announce Type: cross Abstract: The discovery of scaling laws has motivated training neural networks on ever increasing quantities of data. This is typically done with a constant dec
Knowledge catalogue
arXiv:2607.23777v1 Announce Type: cross Abstract: The discovery of scaling laws has motivated training neural networks on ever increasing quantities of data. This is typically done with a constant dec
arXiv:2607.22712v1 Announce Type: cross Abstract: Single-cell light microscopy images have become an important data source for characterizing cell phenotypes, but their complexity and heterogeneity po
arXiv:2510.14717v2 Announce Type: replace-cross Abstract: Increasing the batch size during training -- a ''batch ramp'' -- is a promising strategy to accelerate large language model pretraining. While
arXiv:2607.22713v1 Announce Type: new Abstract: Enterprise IT support knowledge graphs capture rich relationships among cases, users, devices, symptoms, taxonomic categories, root causes, and historic
arXiv:2607.22545v1 Announce Type: cross Abstract: Deploying large language models in financial-services and agentic settings requires safety classifiers that simultaneously handle prompt injection, re
arXiv:2604.07632v2 Announce Type: replace-cross Abstract: Cross-modal representations vary in how easily they can be aligned, and compatibility is generally non-transitive: two modalities may align th
arXiv:2607.23432v1 Announce Type: new Abstract: Decision-makers in learning environments face a dilemma when their short-term optimal actions may not favor their long-term benefits the most. To unders
arXiv:2607.24249v1 Announce Type: new Abstract: Standard depth sensors systematically fail on transparent surfaces, creating corrupted 3D maps and severe navigation hazards. While specialized hardware
arXiv:2607.22699v1 Announce Type: new Abstract: As Large Language Models (LLMs) grow more capable across diverse tasks, their (in)ability to generalize remains difficult to quantify and poorly underst
arXiv:2607.24341v1 Announce Type: new Abstract: Recent studies use Large language models (LLMs) to simulate human opinions and decisions by prompting models with demographic, attitudinal, or persona-b
arXiv:2607.24492v1 Announce Type: new Abstract: The goal of schema integration is, given a set of input schemata or tables, to derive a global, unified schema that is able to represent the concepts, a
arXiv:2607.24588v1 Announce Type: new Abstract: Early warning of extreme weather is essential for mitigating the societal, economic, and environmental risks posed by hazardous weather events. However,
arXiv:2607.23580v1 Announce Type: new Abstract: Existing vector-sketch models treat recognition and generation as separate tasks, leaving a gap for streaming interfaces that must understand a drawing
arXiv:2607.23268v1 Announce Type: new Abstract: Elastic object manipulation (EOM) involves highdimensional, nonlinear, and elastic deformations. The diverse deformation properties of elastic objects s
arXiv:2607.22793v1 Announce Type: cross Abstract: We describe and evaluate BF-ConvUNeXt, a compact bias-free ConvNeXt U-Net for blind additive-white-Gaussian-noise color image denoising, combining fou
arXiv:2607.24007v1 Announce Type: cross Abstract: We revisit contextual optimization from the perspective of policy class design. A desirable policy class should be expressive enough to learn rich con
arXiv:2607.23735v1 Announce Type: cross Abstract: In many real-world scenarios, encountering continual shifts in domain during inference is very common. Consequently, continual test-time adaptation (C
The Information: Sources: Moonshot is seeking access to more Nvidia Blackwell chips to prepare for Kimi K4's development, after training K3 on Nvidia chips, including Blackwell — Beijing-based startup
arXiv:2607.23474v1 Announce Type: new Abstract: This paper develops an online, off-policy policy-iteration framework for reinforcement learning (RL), based on sparse Gaussian-mixture-model Q-functions
arXiv:2607.22732v1 Announce Type: new Abstract: LLM-based game agents often perform poorly on more complex tasks. This work examines whether these failures are linked to limited spatial reasoning and
arXiv:2607.24701v1 Announce Type: new Abstract: Missing modalities in RGBT tracking often lead to incomplete and unstable multimodal feature representations that greatly degrade the performance. Exist
arXiv:2607.10405v2 Announce Type: replace-cross Abstract: Controlling attributes is a critical step toward achieving the final creative outcome, yet current approaches fall short in supporting users i
It's time to experiment using DSpark! Please share your stats(pp/tg improvements). DSpark related stuff to check: DeepSpec - a deepseek-ai Collection DeepSeek-V4 with DSpark - DeepSeek-V4-Pro-DSpark &
arXiv:2307.14544v2 Announce Type: replace-cross Abstract: This paper presents an artificial intelligence tool designed to assist students with dyslexia, ADHD, and short attention spans in processing t
arXiv:2607.23346v1 Announce Type: new Abstract: Modern deep neural networks are potent catalysts for scientific and industrial impact, yet excessive parameter counts impede deployment in low-compute s
arXiv:2607.23123v1 Announce Type: new Abstract: Existing evaluations of large language models cover knowledge, reasoning, coding, and tool use, but they rarely treat a verifiable deliverable produced
arXiv:2603.20248v2 Announce Type: replace-cross Abstract: AI systems are increasingly entrenched in public governance, yet scholarship lacks formal tools to determine when deviations of public trust i
arXiv:2607.22658v1 Announce Type: new Abstract: Speech-to-speech dialogue models increasingly depend on prosody and interactional nuance to convey social intent, yet benchmarks for these cues remain l
arXiv:2607.24191v1 Announce Type: cross Abstract: Conversational stance detection has shifted from static text analysis to dynamic multimodal modeling. However, existing benchmarks exhibit three key l
arXiv:2603.14382v2 Announce Type: replace Abstract: As AI systems are being integrated more rapidly into diverse and complex real-world environments, the ability to perform holistic reasoning over an
arXiv:2607.22798v1 Announce Type: cross Abstract: Computer-use agents are usually improved by strengthening perception: better models for reading a screenshot and choosing where to click. Yet a screen
arXiv:2607.22708v1 Announce Type: new Abstract: Deploying a vision-language model with full UI understanding on end devices has long been trapped between accuracy and efficiency: on one side is the ac
arXiv:2607.24519v1 Announce Type: cross Abstract: Pretrained EEG foundation models are increasingly proposed for clinical decoding, but their transfer across populations and robustness to negative con
arXiv:2607.22778v1 Announce Type: cross Abstract: Robust EEG motor imagery decoding remains limited by strong inter-individual variability, making it difficult to identify pipelines that generalize ac
arXiv:2607.24054v1 Announce Type: new Abstract: A correct answer can conceal why an agent succeeded. Once agents change their information state during evaluation, correctness no longer distinguishes i
Hi everyone! We’ve just released a major update to the leaderboard! We are expanding beyond Python with a new multilingual slice featuring real-world software engineering tasks across 5 languages. Ope
arXiv:2607.23055v1 Announce Type: new Abstract: Chain-of-thought (CoT) prompting can fail severely on constraint-dense logical reasoning tasks, where unverified errors accumulate silently across steps
arXiv:2607.23976v1 Announce Type: cross Abstract: Appending a two-word confirmation tag to a decision question -- 'Is X the better choice?' versus 'X is the better choice, right?' -- changes whether a
arXiv:2607.24130v1 Announce Type: cross Abstract: Tabular data is the dominant structured-data modality, and learning table representations has become a core research direction. Table-level embeddings
arXiv:2606.19259v2 Announce Type: replace-cross Abstract: Text-rich images often contain privacy-sensitive, transactional, or decision-relevant information. As recent multimodal image generation model
arXiv:2607.24063v1 Announce Type: new Abstract: On standard factuality tasks, frontier models now cluster near the top of the scale. The question is therefore shifting from how factual a system is tow
arXiv:2509.13196v2 Announce Type: replace Abstract: Over-prompting, a phenomenon where excessive examples in prompts lead to diminished performance in Large Language Models (LLMs), challenges the conv
arXiv:2607.23335v1 Announce Type: new Abstract: Auxiliary signal pathways in VLMs are routinely fitted with learnable gates so the optimiser can decide how much of the signal to admit. We find that th
arXiv:2607.24032v1 Announce Type: new Abstract: Generative-AI evaluations can become historical before publication, yet calendar age does not affect every conclusion equally. This paper has two linked
The Kimi K3 architecture figure for yesterday's big open-weight model release, along with some observations and thoughts. 1. Yes, it looks relatively complicated, but it's essentially a scaled-up prod
arXiv:2607.18088v2 Announce Type: replace-cross Abstract: Conformal prediction certifies that a classifier's prediction sets cover the truth, and that certificate is marginal. Many recognition benchma
arXiv:2607.22585v1 Announce Type: new Abstract: Public leaderboards for coding agents typically rank systems by model name and pass rate, while the surrounding harness (the scaffold that issues tools,
arXiv:2607.24276v1 Announce Type: cross Abstract: Large language models (LLMs) process text through subword tokenizers rather than directly reading characters or words. Because these tokenizers are tr
It has only been two days since I move 100% from Qwen3.5-27B F16 to ThinkingCap-Qwen3.6-27B F16. Where I was getting tps in 30-40 range (depending on the size of the context), I am definitely getting
arXiv:2607.23054v1 Announce Type: cross Abstract: Multi-head Latent Attention (MLA), introduced in DeepSeek-V2, compresses key-value pairs through a shared low-rank bottleneck (cKV), achieving 81% KV-
arXiv:2607.23951v1 Announce Type: new Abstract: Video temporal grounding (VTG) aims to localize the continuous video interval described by a natural-language query. However, current VLM-based methods
Workflow automation company Tines Security Services Ltd. today launched Tines 3B, an artificial intelligence-native platform for building, running and governing enterprise workflows, applications and
arXiv:2607.23425v1 Announce Type: cross Abstract: Large language models increasingly write TLA^{+} formal specifications from natural-language descriptions, but progress is hard to measure: existing r
arXiv:2607.22762v1 Announce Type: cross Abstract: Causal inference has become a central issue across various fields, including computer science, statistics, economics, education, healthcare, and medic
arXiv:2607.22610v1 Announce Type: new Abstract: When a language model produces a response in a multi-turn conversation, which tokens from prior turns shaped that answer, and how did those dependencies
arXiv:2607.22625v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) enhances large language models (LLMs) with external knowledge, but suffers from knowledge conflicts: when retrieved
arXiv:2607.22954v1 Announce Type: new Abstract: Objective: To characterize the kinds of internal documentation inconsistencies a general-domain large language model (LLM) can surface from real-world d
arXiv:2607.24081v1 Announce Type: cross Abstract: Brain-machine interfaces (BMIs) can assist individuals with limited mobility, such as stroke survivors or amputees. One of the key challenges in devel
arXiv:2607.23404v1 Announce Type: new Abstract: Self-driving laboratories increasingly rely on multi-fidelity Bayesian optimization (MFBO) to balance cheap, approximate evaluations against scarce, exp
arXiv:2607.22661v1 Announce Type: new Abstract: Diffusion large language models (D-LLMs) have recently gained increasing attention, yet their reliability is significantly hindered by the hallucination