Knowledge catalogue
arXiv:2607.17425v3 Announce Type: replace Abstract: Sparse autoencoders (SAEs) compress model activations into sparse codes, but equal reconstruction error and sparsity can preserve different linearly
arXiv:2512.08379v3 Announce Type: replace Abstract: Biosignals collected from wearable devices are widely utilized in healthcare applications. Machine learning models used in these applications often
arXiv:2609.15422v1 Announce Type: new Abstract: AI agents are provisioned the same as employee-owned hosts in many enterprise settings with a static credential set fixed at deployment which includes a
arXiv:2609.13640v1 Announce Type: new Abstract: Encoder-based time series foundation models (TSFMs) typically rely on deep stacks of independently parameterized Transformer layers, where only the fina
One thing I love about both Qwen 3.8 27B and Flash Next is the effort it puts in to make a good product. It is the opposite of a lazy model and 'good enough' is never what aims to accomplish. It goes
arXiv:2609.15571v1 Announce Type: new Abstract: As deep learning models become fundamental to modern healthcare, the 'Right to be Forgotten' mandated by privacy regulations like GDPR and HIPAA necessi
arXiv:2609.13745v1 Announce Type: new Abstract: Vision--language models (VLMs) can answer chart questions accurately, but output accuracy does not show how they combine the evidence needed to recover
arXiv:2609.13917v1 Announce Type: new Abstract: Energy-Based Models (EBMs) provide a flexible framework for generative modeling by learning an energy landscape that assigns low energy values to realis
arXiv:2609.15871v1 Announce Type: cross Abstract: Rising societal and lifestyle complexity has been linked to a growing prevalence of mental distress worldwide. Educational institutions, workplaces, c
arXiv:2511.19046v2 Announce Type: replace-cross Abstract: Medical image segmentation is fundamental for biomedical discovery. Existing methods lack generalizability and demand extensive, time-consumin
arXiv:2609.14976v1 Announce Type: new Abstract: Long-horizon LLM agents accumulate memory across sessions, creating sparse but high-impact risks: stale facts, conflicting updates, cross-user leakage,
arXiv:2609.13685v1 Announce Type: cross Abstract: Negation remains a longstanding challenge for both language models (LMs) and large language models (LLMs). Prior work mainly focuses on a small set of
Know everything. Do anything. That was the message NVIDIA founder and CEO Jensen Huang brought to Salesforce Dreamforce Tuesday, joining CEO Marc Benioff onstage in an appearance that coincided with t
arXiv:2609.13810v1 Announce Type: cross Abstract: One-vs-rest rankers that show each user the top-K of many rare labels usually counter imbalance with a per-label positive-class weight, scale_pos_weig
arXiv:2609.14615v1 Announce Type: cross Abstract: Unified motion generation and understanding is crucial for embodied AI systems that can both synthesize and interpret human actions in open-world envi
arXiv:2609.13734v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly deployed in real-world high-stakes applications, effective governance has become essential. Existing
arXiv:2609.13507v1 Announce Type: new Abstract: Brain-computer interfaces (BCIs) decode neural activity to restore lost function. Typically, training a high-performance neural decoder requires a large
arXiv:2609.14025v1 Announce Type: new Abstract: Forward-looking sonar object detection is essential for underwater perception, yet deployment on embedded platforms requires highly compact models. To a
arXiv:2609.13982v1 Announce Type: cross Abstract: In Human-Robot Interaction, the standard approach to learn a reward model that represents human preferences for robot behavior consists of three steps
arXiv:2609.13463v1 Announce Type: new Abstract: The increasing deployment of AI agents in long-horizon tasks yields massive execution logs. Diagnosing failures within these records is crucial for reli
arXiv:2609.15022v1 Announce Type: new Abstract: Defense is a knowledge-intensive domain that requires precise understanding of specialized terminology, doctrinal concepts, operational procedures, and
arXiv:2502.20099v3 Announce Type: replace-cross Abstract: We evaluate methods for causal representation learning (CRL) on a simple, real-world system that satisfies the basic problem setup of CRL. The
arXiv:2609.14882v1 Announce Type: cross Abstract: Nucleotide sequence analysis is central to problems spanning regulatory genomics, evolutionary biology, and phenotype prediction. Classical bioinforma
arXiv:2609.14278v1 Announce Type: cross Abstract: Accurate sperm detection is essential for computer-assisted semen analysis, yet it remains challenging in microscopic images due to dense distribution
arXiv:2609.15983v1 Announce Type: new Abstract: Language models can produce plausible short proofs, but may still be unreliable on long-horizon research problems, where progress depends on a sequence
arXiv:2609.13267v1 Announce Type: new Abstract: Scientific charts encode quantities in axes, legends, and geometric marks, yet large vision-language models still treat them as natural photographs. Vis
arXiv:2510.23039v2 Announce Type: replace Abstract: Approximate Nearest Neighbor (ANN) search and Approximate Kernel Density Estimation (A-KDE) are fundamental problems at the core of modern machine l
arXiv:2609.13226v1 Announce Type: new Abstract: Machine learning for neglected tropical diseases is limited by data, not algorithms: public annotated image sets for leprosy (Hansen's disease) number i
arXiv:2609.14118v1 Announce Type: cross Abstract: Online understanding of who is talking to the camera wearer is a key capability for egocentric social interaction. However, existing talk-to-me (TTM)
arXiv:2609.14124v1 Announce Type: cross Abstract: Medical image analysis is often hindered by biased datasets, which can lead to biased models and limited clinical applicability. A promising strategy
What's Changed app: fix ChatGPT model selector spacing mlxrunner: Evict prefix cache snapshots from the active conversation mlxrunner: check system free memory and wait for evicted runners before load
arXiv:2609.15106v1 Announce Type: new Abstract: Large language models can hallucinate even when the knowledge required for a correct answer is already available. We study this failure through a latent
arXiv:2609.12470v1 Announce Type: new Abstract: Customer churn is one of the major issues in the telecommunication industry. To predict customer churn, conventional centralized machine learning approa
arXiv:2609.12264v1 Announce Type: new Abstract: Designing effective chemotherapy regimens is hindered by tumor heterogeneity and drug resistance, which complicate the deployment of patient-specific mo
OverviewAs enterprises scale their AI and agentic workflows, they require serverless platforms that make data preparation for model training, evaluation, and inference effortless and efficient. Datafl
arXiv:2601.16982v2 Announce Type: replace Abstract: Modern generative video models excel at producing convincing, high-quality outputs, but struggle to maintain multi-view and spatiotemporal consisten
arXiv:2604.05793v2 Announce Type: replace-cross Abstract: In LLM agent pipelines, prompt privacy risk propagates beyond a single model call: raw user content enters retrieval queries, memory writes, t
arXiv:2609.12444v1 Announce Type: cross Abstract: Simulated societies of large language model agents are used to study online polarization, and separately to study collective intelligence, but the two
arXiv:2609.12446v1 Announce Type: cross Abstract: Social-deduction games such as Werewolf are increasingly used to evaluate LLM agents, but existing evaluations often rely on final game outcomes. We p
arXiv:2602.15329v2 Announce Type: replace Abstract: Online video understanding requires models to perform continuous perception and long-range reasoning within potentially infinite visual streams. Its
arXiv:2609.12705v1 Announce Type: new Abstract: Handwritten text recognition resources are often small and distributed across collections that differ in language, script, document structure, and annot
We are excited to share that Google Cloud was named a Leader and received the highest score in the ‘current offering’ category in the Forrester Wave™: Public Cloud Platforms, Q3 2026 report, which exa
arXiv:2609.12408v1 Announce Type: new Abstract: Hazardous-freight operations at petrochemical logistics nodes are safety-critical for intelligent transportation systems, yet existing vision benchmarks
arXiv:2510.18368v2 Announce Type: replace Abstract: We present extbf{Korean SimpleQA (KoSimpleQA)}, a benchmark for evaluating factuality in large language models (LLMs) with a focus on Korean cultura
arXiv:2609.12127v1 Announce Type: new Abstract: Prompt-policy editing offers a practical way to improve agents that synthesize executable workflows without updating the underlying model. However, pers
arXiv:2609.12367v1 Announce Type: cross Abstract: Membership inference attacks (MIAs) are the standard tool for auditing the privacy risks of machine learning models. Given a query point, an MIA aims
arXiv:2609.12081v1 Announce Type: cross Abstract: Mobile manipulation requires perceptual evidence at different spatial scales for base motion and arm control, while the two action modalities remain k
arXiv:2609.12686v1 Announce Type: cross Abstract: Large language models (LLMs) process long contexts, including long documents and lengthy conversations, but face token-level memory usage that increas
arXiv:2609.12814v1 Announce Type: new Abstract: Linear attention and state-space models provide linear-time sequence modeling, but their recurrent memory remains a second-order tensor (a matrix), limi
arXiv:2609.12455v1 Announce Type: new Abstract: Automated machine learning (AutoML) is reshaping data-driven science and industrial practice, and as large language models are introduced into AutoML, p
arXiv:2609.12331v1 Announce Type: new Abstract: Simulated students generated by computational models provide a practical way to evaluate tutoring strategies and pedagogical approaches used by human an
arXiv:2609.12343v1 Announce Type: new Abstract: Feed-forward Gaussian splatting models have demonstrated remarkable effectiveness in reconstructing three-dimensional (3D) objects from a few two-dimens
The first generation of our 150M model has just been released Its performance is similar to that of GPT2-Small The benchmarks: PIQA: 62.24% Hellaswag: 32.20% Arc-Easy: 44.91% Arc-Challenge: 25.00% Ari
VLLM Benchmark: Prefill, Prompt processing - avg, 871.93 tok/s (3 hours constant running xhigh) - 10K prompt, 1000.26 tok/s (16 runs) - 90K prompt, 743,59 tok/s (16 runs) Decode, tok gen - avg, 38.39
I'll start by saying I'm not talking about the models themselves, I'm aware that I can't come close to something like Fable's intelligence locally. Just wanted to get that out of the way. Basically. O
Should you build an agent harness? I see lots of opinions about it. My thoughts: As an AI engineer, learning how to build a harness is one of the best ways to stay ahead and unlock unique value from a
Hey everyone, Giving AI agents access to MCP tools or shell commands is awesome, but prompt injection is still a huge headache. If an agent reads an untrusted document containing `ignore previous inst
Wild 24 hours for AI and lots of different proposals have been made. TLDR; the only *tangible* new fact is that OpenAI and Anthropic are going to have embedded 3rd party evaluators from unknown organi
I find this new model at HF: 'Built for demanding work. A 262 144-token context window, adjustable reasoning effort, tool calling, and text, image and video understanding. Architecture Agnes-3.0-Flash
arXiv:2609.11224v1 Announce Type: cross Abstract: Sports data analysts translate domain questions into insights by combining computation with sport-specific domain expertise. Large language models eas