Knowledge catalogue
arXiv:2609.36546v1 Announce Type: cross Abstract: On-policy distillation (OPD) trains a student model on its self-generated trajectories with dense token-level teacher feedback. However, naive OPD may
arXiv:2609.36500v1 Announce Type: cross Abstract: Speaker verification systems encounter combinations of noise, channel distortion, and changes in speech. Evaluating each condition separately does not
Jyoti Mann / The Information: Internal data: Meta's Muse now has 3M+ users who submit at least one prompt per week and 1M+ DAUs who have sent at least one prompt — Meta Platforms' Muse now has more th
arXiv:2609.37170v1 Announce Type: cross Abstract: Off-policy and on-policy distillation have traditionally been formulated as separate paradigms, each favoring a different property of distillation tra
arXiv:2609.37114v1 Announce Type: new Abstract: DANCo (Dimensionality from Angle and Norm Concentration) jointly calibrates nearest-neighbor distance and angular statistics and consistently reaches st
arXiv:2609.36709v1 Announce Type: cross Abstract: Out-of-distribution (OOD) generalization is a central challenge in scientific machine learning. We study regression problems in which the test distrib
arXiv:2609.35948v1 Announce Type: cross Abstract: Geometry does more than constrain an associative memory: curvature determines what it remembers and which states it creates. We develop intrinsic dens
Amazon Bedrock now supports Anthropic's Claude Opus 5 and Claude Sonnet 5 with in-region inference in Seoul, and Claude Sonnet 5 in Singapore. If you have local data processing requirements in South K
Introducing MCP Sharing, built into FlyMyAI infra. Configure FlyMy MCP once: 1500+ MCPs inside, from Telegram and Slack to Instagram and Brex. Use it from Claude, Codex or any agent. Share it with you
SynthID Bio is a protein‑generation platform developed by AlphaProteo that delivers custom-designed peptides for use in biology and health research. It was highlighted in the September 2024 issue of *
arXiv:2609.36061v1 Announce Type: new Abstract: In quantitative finance, standard regression losses are misaligned with the economics of return prediction. As the conditional mean of financial log-ret
arXiv:2609.36451v1 Announce Type: cross Abstract: Large language models often preserve meaning despite substantial changes in wording, style, and syntax, while small semantic edits can systematically
arXiv:2609.36860v1 Announce Type: new Abstract: We present IronLLM-0.6B, a 654M-parameter language model designed for efficient on-device inference. IronLLM-0.6B combines a hybrid attention architectu
arXiv:2606.21804v2 Announce Type: replace-cross Abstract: Maintainability is a core dimension of software engineering, shaping how code is written, reviewed, and developed over time. While coding agen
arXiv:2609.35868v1 Announce Type: new Abstract: Is human readability necessary for effective fine-tuning of large language models? We investigate whether model-conditioned training representations can
arXiv:2609.37849v1 Announce Type: cross Abstract: Scientific software is increasingly required to process larger datasets while maintaining acceptable execution times. Software optimization traditiona
arXiv:2609.37043v1 Announce Type: new Abstract: Sampling from unnormalized distributions over large discrete state spaces becomes difficult when a multimodal target is far from a tractable reference.
arXiv:2609.37891v1 Announce Type: new Abstract: Current pre-training datasets are derived from web crawls, with all their issues, and were not designed to support mid- and post-training pipelines--for
arXiv:2609.37863v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly used in place of human annotators, making it important that substitutability tests reflect the model ra
arXiv:2609.38065v1 Announce Type: cross Abstract: Training agents to follow arbitrary instructions is an important goal of multi-task reinforcement learning (RL). Linear temporal logic (LTL) provides
arXiv:2609.26550v3 Announce Type: replace Abstract: LLM-as-a-judge scales evaluation, but reasoning judges are slow and costly. We study JEV-as-a-Judge: evaluation with JEV, a decision-only judge that
arXiv:2606.13345v2 Announce Type: replace Abstract: Existing 3D scene editing methods typically rely on per-scene optimization over explicit 3D representations or cascaded edit-and-reconstruct pipelin
arXiv:2609.36966v1 Announce Type: cross Abstract: Covariate effects vary across contexts and shift over time, requiring forecasters to assess how to use them for each forecasting context. As forecasti
arXiv:2609.36705v1 Announce Type: new Abstract: LLM judges are inherently subjective, often favoring different responses in pairwise comparison when neither option is objectively wrong. To study this
arXiv:2609.35443v2 Announce Type: replace Abstract: Large-scale routing problems are difficult to solve efficiently as their search spaces grow rapidly with problem size. Existing approaches primarily
arXiv:2609.35938v1 Announce Type: new Abstract: This paper proposes an interpretable neural operator framework, the Kernel Operator Network (KernelOnet), which incorporates kernel functions explicitly
arXiv:2609.36676v1 Announce Type: new Abstract: We present a straightforward but effective method for repurposing existing contact-rich dexterous manipulation demonstrations. Starting from inputs of h
arXiv:2609.36695v1 Announce Type: new Abstract: Self-distillation turns knowledge distillation into a closed learning loop and offers a path toward recursive self-improvement. Without an external teac
arXiv:2609.33142v2 Announce Type: replace Abstract: Generating a correct answer does not mean that a language model will select it. We separate factual recall into three steps: generating a correct ca
arXiv:2609.36115v1 Announce Type: new Abstract: Industry applications often demand low-latency classification, yet current large language model (LLM) approaches remain poorly suited for latency-critic
arXiv:2609.37958v1 Announce Type: new Abstract: As the input dimension n grows, rule-based machine learning, such as Learning Classifier Systems (LCSs), faces a fundamental scalability bottleneck for
arXiv:2609.36151v1 Announce Type: new Abstract: Humanoids now walk, balance and reach with remarkable generality: one whole-body tracking policy follows references from a human, or from an end-to-end
arXiv:2609.37473v1 Announce Type: cross Abstract: Many engineering problems involve optimizing a high-dimensional expensive black-box (HEB) design space. To solve such problems efficiently, we propose
arXiv:2609.37673v1 Announce Type: new Abstract: Experienced professionals know more than just facts and conclusions. They know which cues matter, why a judgment is reasonable, and which action to take
arXiv:2609.37988v1 Announce Type: new Abstract: As the context size of text processed with an LLM grows, the size of KV caches can outstrip the memory allocated for the original model weights. This im
arXiv:2609.37481v1 Announce Type: new Abstract: Large-scale pervasive sensing increasingly relies on high-resolution satellite imagery, yet task-specific onboard vision is constrained by costly annota
arXiv:2609.37024v1 Announce Type: new Abstract: Integrating transcriptomic and electrophysiological data is essential for building multimodal foundation models for neuroscience. Patch-seq provides pai
arXiv:2609.36139v1 Announce Type: cross Abstract: As large language models are deployed in increasingly autonomous long-horizon tasks, manually auditing and verifying the actions, artifacts, and outpu
arXiv:2609.35779v1 Announce Type: cross Abstract: Given recent achievements of large language models (LLMs), frontier models are expected to perform well on Bayesian reasoning tasks, at least as well
arXiv:2609.36515v1 Announce Type: cross Abstract: A common assumption in language model development is that cognitive abilities are organized around a general, domain-free intelligence factor, like fl
arXiv:2609.37497v1 Announce Type: new Abstract: Modern transformer models excel at capturing semantic relationships through sentence embeddings, yet their ability to perform pragmatic reasoning remain
Last night, we hosted our monthly @daytonaio AI Builders Demo Night at the @WorkOS office in San Francisco! Great demos, conversations, and energy from the AI builder community. Huge thanks to @llama_
Last Week in AI #345 notes that Anthropic and OpenAI are in a close race to launch more capable but cheaper models this month: Anthropic unveiled Claude Opus 5.5 with stricter cybersecurity safeguards
arXiv:2609.37017v1 Announce Type: new Abstract: LLM-based multi-agent systems (MAS) increasingly use latent collaboration to avoid the information loss and repeated encoding-decoding overhead of natur
arXiv:2609.38058v1 Announce Type: cross Abstract: Time Series Foundation Models (TSFMs) currently provide state-of-the-art results in forecasting tasks. They are available out-of-the-box and rely on i
arXiv:2609.36371v1 Announce Type: cross Abstract: Test-time scaling improves software engineering agents by generating multiple candidate trajectories and selecting the best one. Verifying and selecti
arXiv:2609.36707v1 Announce Type: new Abstract: Legal contracts contain ambiguities that expose enterprises to financial and legal risks. Some ambiguities allow flexible interpretation without trigger
arXiv:2609.38027v1 Announce Type: new Abstract: In recent years, the performance of large language models (LLMs) on reasoning tasks has been remarkable, even surpassing human capabilities on various b
arXiv:2609.37426v1 Announce Type: cross Abstract: Modern vision-language models (VLMs) have shown promising results in long-video understanding due to the rich semantic information they can capture. H
arXiv:2609.37080v1 Announce Type: new Abstract: Latent Diffusion Models (LDMs) typically adopt a two-stage pipeline: an auto-encoder (AE) is first pre-trained to define a latent space, then a diffusio
arXiv:2609.38166v1 Announce Type: cross Abstract: Recent LLMs increasingly adopt hybrid designs that replace standard attention with linear attention, such as Gated DeltaNet (GDN) and Kimi Delta Atten
arXiv:2609.36932v1 Announce Type: new Abstract: Recently, Group Relative Policy Optimization (GRPO) and its variants have been developed for policy optimization and demonstrated notable performance ga
Google announced **Gemini 4 Argon**, described as the next generation of frontier intelligence in a September 30, 2026 blog post on Google AI’s site. The model represents an evolution of the Gemini se
arXiv:2609.35911v1 Announce Type: cross Abstract: Adapting large language model agents during deployment requires not only retaining past experience, but also turning new observations into timely guid
arXiv:2609.35848v1 Announce Type: new Abstract: On-board compression of synthetic aperture radar (SAR) phase history is bandwidth-critical, and block-adaptive quantization (BAQ) remains the operationa
arXiv:2609.36698v1 Announce Type: new Abstract: To reduce the number of parameters and cache memory requirements of transformers we introduce dual-headed transformers instead of three heads. We studie
arXiv:2609.36587v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a prominent approach for improving language-model performance on reasoning tasks using
arXiv:2609.37586v1 Announce Type: cross Abstract: Continual audio deepfake detection requires learning newly emerging deepfake methods while retaining discrimination of previously encountered speech.
arXiv:2609.37868v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) methods such as GRPO rely on successful self-generated trajectories, but finite rollout budgets
arXiv:2609.37664v1 Announce Type: new Abstract: Causal Normalizing Flows (CNFs) enable causal inference from observational data given the causal structure, but they assume fully observed training data