Knowledge catalogue
arXiv:2607.20890v1 Announce Type: new Abstract: On-device federated learning (FL) enables privacy-preserving and personalized model training on resource-constrained devices such as smartphones and IoT
.@Kimi_Moonshot K3 lands on Together on Monday! We ran 452 DeepSWE rollouts against Claude Fable 5: near-flagship coding at ~35% of the price, and K3 pulls ahead at higher pass@k's. Full deep-dive: ht
arXiv:2607.11029v2 Announce Type: replace-cross Abstract: Recent progress in visual navigation has largely been driven by scale: end-to-end policies with hundreds of millions of parameters trained on
arXiv:2512.07540v4 Announce Type: replace-cross Abstract: Error Span Detection (ESD) extends automatic machine translation (MT) evaluation by localizing translation errors and labeling their severity.
arXiv:2607.20940v1 Announce Type: new Abstract: Streaming video diffusion models have made substantial progress toward interactive and dynamic world simulation, but the nested autoregressive and denoi
arXiv:2607.21290v1 Announce Type: cross Abstract: Multi-task learning (MTL) is a promising approach for prediction tasks derived from video game state data, as modern game telemetry provides multiple
New research with Microsoft's and colleagues on training agents inside the harnesses they actually run in. (bookmark it) Why it matters: Agents today live inside elaborate harnesses like Claude Code,
arXiv:2607.21080v1 Announce Type: new Abstract: Long-horizon weather forecasting is a fundamental challenge in atmospheric science, for which autoregressive Deep Learning Weather Prediction (DLWP) has
When we introduced the Open Knowledge Format (OKF) in June 2026, we asserted that the context that agents need (table schemas, metric definitions, runbooks) should live in a format, not in a proprieta
Open weights = freedom. You can run them on your own hardware. No vendor can pull the plug. No API can deprecate you. No company logs your private data. That's sovereignty. Closed models hand one comp
arXiv:2607.20492v1 Announce Type: cross Abstract: Language models in production do not write prose. They fill forms: JSON fields, function arguments, extraction templates. We show that the form itself
arXiv:2607.20653v1 Announce Type: cross Abstract: Predicting how deformable objects evolve under robotic manipulation is a longstanding challenge. Existing approaches typically rely on per-object opti
arXiv:2607.20628v1 Announce Type: cross Abstract: Real-world video deblurring remains challenging due to diverse motion patterns, complex degradations, and the scarcity of realistic training data, yet
arXiv:2607.20515v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) is critical for aligning Large Language Models (LLMs) with human preferences. However, its efficacy is
arXiv:2607.20481v1 Announce Type: new Abstract: Local-cloud collaboration is a practical way to deploy large language models under resource constraints, but existing methods often rely on trained rout
arXiv:2607.16619v2 Announce Type: replace Abstract: Safe and socially compliant navigation in open human-robot environments requires robots to reason about heterogeneous participants with different dy
arXiv:2510.04019v3 Announce Type: replace-cross Abstract: Diffusion large language models (dLLMs) represent a promising alternative to autoregressive LLMs; however, the lack of effective post-training
arXiv:2607.21239v1 Announce Type: new Abstract: Polarization cues benefit applications such as material detection and de-reflection, yet acquiring them typically requires dedicated hardware. This moti
arXiv:2607.20545v1 Announce Type: new Abstract: Diffusion models have become competitive generators for time series, but their practical use is limited by the large number of sequential denoising step
arXiv:2607.21433v1 Announce Type: cross Abstract: Chain-of-thought reasoning models such as DeepSeek-R1-Distill-Qwen-7B exhibit a bimodal convergence pattern: generations either terminate within a tok
arXiv:2512.16615v2 Announce Type: replace Abstract: Diffusion Transformers (DiTs) set the state of the art in visual generation, yet their quadratic self-attention cost fundamentally limits scaling to
arXiv:2607.21090v1 Announce Type: cross Abstract: We propose a Reinforcement Learning (RL) method to directly optimize the faithfulness of self-explanations - the extent to which a model's generated r
arXiv:2607.20977v1 Announce Type: new Abstract: Metal artifacts generated by dental implants significantly degrade cone-beam computed tomography (CBCT) volumes, obscuring critical anatomical structure
arXiv:2607.20474v1 Announce Type: new Abstract: Natural language interfaces can greatly benefit the accessibility and usability of optimization modeling, and recent advances in large language models (
arXiv:2607.21556v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) is promising as it removes the external teacher required by on-policy distillation (OPD), yet it still needs asymme
arXiv:2607.19782v1 Announce Type: cross Abstract: Kernel methods are powerful tools in machine learning but commonly used full-Gram kernels face three key limitations: (1) quadratic scaling with train
Agentic AI compute has become the defining workload of the cloud’s next era, reshaping how hyperscalers, neo-clouds and enterprises architect their infrastructure. As autonomous agents move into produ
arXiv:2607.19190v2 Announce Type: replace-cross Abstract: Real-to-sim conversion for robotic interaction with objects remains labor-intensive because it requires more than visual reconstruction: a str
Advanced Micro Devices Inc. is pushing harder than ever to grab even more market share from Nvidia Corp. in the artificial intelligence chip industry. At its Advancing AI 2026 event today in San Franc
arXiv:2607.19742v1 Announce Type: cross Abstract: Cyber Threat Intelligence (CTI) reports richly describe real-world attack processes, but their unstructured narratives cannot be directly used for aut
arXiv:2607.19726v1 Announce Type: new Abstract: Automatic pain localization, which involves identifying the anatomical origin of pain from peripheral physiological signals without patient self-report,
arXiv:2607.09988v3 Announce Type: replace-cross Abstract: Recommendation systems, from traditional multi-stage to recent unified generative architectures, face challenges in incorporating diverse cont
At the moment MLX (and Llama.cpp for Macs) run 16bit activations everywhere. Despite this, the M5 generation silicon actually does support INT8 activations - it actually allows w4a8 d_type. It's just
arXiv:2607.11338v2 Announce Type: replace Abstract: Symbolic expressions can effectively characterize and predict circuit behavior, but deriving them directly from circuit schematics is challenging. T
Catch @pavneet1990 at Builder's Day this Friday! I will be at @goannacapital 's Builders Day in SF this Friday, speaking alongside leaders from @ElevenLabs , @AnthropicAI and @DecagonIns If you are ar
arXiv:2511.05865v3 Announce Type: replace-cross Abstract: Recent advancements in large-scale generative models have enabled the creation of high-quality images and videos, but have also raised signifi
arXiv:2607.18779v1 Announce Type: new Abstract: In India, crop germination is primarily monitored by visual inspection and manual counting, which are prone to errors, despite their crucial role in det
arXiv:2607.19996v1 Announce Type: new Abstract: Machine Learning models are widely used for automating classification tasks by extracting statistical patterns from data. However, their performance det
arXiv:2607.18716v1 Announce Type: new Abstract: Video multimodal large language models have shown strong capability in video understanding, yet their adaptation to sequentially evolving domains remain
arXiv:2607.20086v1 Announce Type: cross Abstract: State-space sequence models are attractive for streaming speech because they maintain compact recurrent state, but scan-style training kernels can hav
arXiv:2607.19879v1 Announce Type: new Abstract: Infrared and visible image fusion (IVIF) integrates the complementary information of two modalities into a single image with richer scene content. While
arXiv:2607.18700v1 Announce Type: new Abstract: The FathomNetCLEF 2026 competition combines underwater object detection and fine-grained marine species classification under a positive-unlabeled evalua
arXiv:2607.19894v1 Announce Type: cross Abstract: Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs. Existing defenses generally fall into
arXiv:2607.20087v1 Announce Type: new Abstract: Aims: Cardiovascular magnetic resonance (CMR) imaging enables non-invasive assessment of myocardial structure, function, and pathology, but requires sub
arXiv:2601.21026v2 Announce Type: replace-cross Abstract: Sampling configurations at thermodynamic equilibrium is a central challenge in statistical physics. Boltzmann Generators (BGs) tackle it by co
arXiv:2607.19809v1 Announce Type: cross Abstract: In multi-agent reinforcement learning (MARL), inter-agent communication is effective for improving performance under partial observability. Representa
arXiv:2607.19375v1 Announce Type: cross Abstract: Language models perform economically valuable work, yet they are not currently assessed for how well they perform every economically valuable task. We
arXiv:2607.19932v1 Announce Type: new Abstract: Spoken language models (SLMs) enable natural human-computer interaction, but their reasoning ability still lags behind that of text-based large language
arXiv:2607.20073v1 Announce Type: new Abstract: AI-based recruitment systems that rely on machine learning models trained on historical CV data, risk perpetuating and amplifying social biases. A key c
arXiv:2607.19962v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) often suffer from overthinking due to redundant verification steps. Existing approaches for mitigating overthinking, such
arXiv:2607.20072v1 Announce Type: new Abstract: Deep gaze estimation works well in controlled capture but degrades in unconstrained settings, where systems must reject unreliable predictions. Single-p
arXiv:2607.20141v1 Announce Type: cross Abstract: The rapid growth of chiplet-based artificial intelligence systems-on-chip (SoCs) has exposed a fundamental gap in semiconductor test methodology. Exis
arXiv:2607.09530v2 Announce Type: replace Abstract: We introduce Freya-TTS, a compact, tokenizer-free, Turkish-first text-to-speech model designed for highly reliable and efficient conversational synt
arXiv:2607.20071v1 Announce Type: new Abstract: Vision-centric 3D occupancy prediction provides dense scene representations essential for autonomous driving and robotic navigation, yet existing method
arXiv:2607.20010v1 Announce Type: new Abstract: In this paper, we present a generalized temporal-difference (TD) reinforcement learning framework based on the theory of conditional expectations. The v
arXiv:2607.18703v1 Announce Type: new Abstract: Generative world renderer AlayaRenderer receives structured world states exported from physics engines and synthesizes RGB frames. Unlike models that ge
arXiv:2607.09080v2 Announce Type: replace Abstract: Although Video Large Language Models (Video LLMs) have shown strong performance in video understanding, their efficiency is still limited by the lar
arXiv:2607.20171v1 Announce Type: cross Abstract: Learned solvers for compressible flow are usually compared to classical methods at equal mesh resolution rather than at equal computational cost, and
arXiv:2607.19398v1 Announce Type: new Abstract: Multi-entity compositional questions pose significant challenges to existing retrieval-augmented language models. Conventional methods fall into a dilem
arXiv:2607.19228v1 Announce Type: new Abstract: Real-world spatial intelligence requires agents to understand scenes from continuous video streams, where objects move, persist, disappear, and reappear