Knowledge catalogue
arXiv:2608.13817v1 Announce Type: cross Abstract: Human speech production is constrained by physiology, giving rise to characteristic temporal structure on acoustic signals. We hypothesise that these
arXiv:2608.14490v1 Announce Type: new Abstract: We present a Test-time World-model Inference (Twin) system, in which a frontier coding agent writes an executable world model for completing continual l
Including the rationalisation for the data below - this is a more robust version of an earlier post I did similar to this - explaining below: How I chose the comparisons The basic question I’m trying
Physical AI evals are starting to become a real category. Until recently, most VLA evaluation was basically: LIBERO → success rate → leaderboard. Now we're seeing a much broader stack emerge: • Allen
We tuned an AI agent that can do large-scale document extraction from long docs (50+ pages, some with 10k-100k fields) with 94%+ accuracy 📈 It uses a harness + model set that is tuned specifically for
arXiv:2608.12700v1 Announce Type: new Abstract: Systems that generate GPU kernels with language models report high correctness rates. Those rates come from a single loose test: run the kernel on a few
If you scroll down from the countdown at https://huggingface.co/Qwen/Qwen3.8-27B, you see a big model card with a bunch of sections: Highlights, Model Overview, Quickstart, Best Practices, Citation, e
arXiv:2608.12522v1 Announce Type: new Abstract: LLM-based program evolution systems such as FunSearch and AlphaEvolve have shown strong ability to discover novel algorithms, but typically optimize eac
arXiv:2608.12629v1 Announce Type: new Abstract: GPU kernel agents and GPU programming languages have advanced separately, leaving expert kernels difficult to reproduce. Agents usually treat the compil
arXiv:2608.12555v1 Announce Type: new Abstract: Predictive explanation methods attribute a model output; they do not, by themselves, attribute an intervention effect on the real-world outcome. We intr
arXiv:2608.12345v1 Announce Type: new Abstract: Language models are increasingly deployed as co-scientists, yet their ability to uphold research integrity under institutional pressure remains unmeasur
arXiv:2608.12441v1 Announce Type: cross Abstract: Deep learning detectors for anomalies in dynamic graphs have reached strong accuracy, yet they remain opaque: when an edge is flagged, the analyst rec
arXiv:2608.12720v1 Announce Type: cross Abstract: While Large Language Model (LLM) agents increasingly rely on long-term memory for persistent interactions, the retrieval mechanisms governing this mem
arXiv:2608.12611v1 Announce Type: new Abstract: Existing screenshot-to-code systems face a trade-off between flexibility and controllability. Direct multimodal generation can hallucinate visible detai
arXiv:2608.12683v1 Announce Type: cross Abstract: Embodied agents must often identify and interact with objects based on their function rather than their identity, requiring them to actively acquire o
arXiv:2608.12843v1 Announce Type: cross Abstract: Text-based person anomaly retrieval aims to retrieve pedestrians exhibiting anomalous behaviors from a large image gallery using natural language desc
arXiv:2608.12724v1 Announce Type: new Abstract: Few-shot in-context learning (ICL) with multi-modal large language models (MLLMs) enables task adaptation without parameter updates, but its performance
Chinese artificial intelligence developer Z.ai Co. today debuted GLM-5.3, an open-source large language model that set records across several popular benchmarks. The LLM is based on an algorithm calle
arXiv:2608.11947v1 Announce Type: cross Abstract: Multiple-choice benchmarks are widely used to evaluate large language models, but MCQ scores conflate knowledge with sensitivity to option order, whic
arXiv:2511.20597v2 Announce Type: replace-cross Abstract: The integration of artificial intelligence (AI) agents into web browsers introduces security challenges that go beyond traditional web applica
arXiv:2608.11492v1 Announce Type: cross Abstract: IoT firmware vulnerability detection remains challenging due to heterogeneous firmware ecosystems, resource-constrained platforms, and limitations in
Ive been experimenting with task-aware GGUF quants for months, taking inspiration from TASA and TAQO but pushing the allocation lower to to the tensor level. The basic idea is to generate a custom ima
arXiv:2608.11922v1 Announce Type: new Abstract: Predictive-distribution entropy makes a strong selection rule in retrieval-augmented question answering: across five QA benchmarks, keeping the candidat
arXiv:2608.11941v1 Announce Type: new Abstract: We construct OEIS Open, a benchmark based on 492 open mathematical conjectures from the OEIS, formalized in Lean by Tsoukalas et al. Whereas these conje
arXiv:2505.03818v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) can achieve strong performance on everyday coding tasks, but they can fail on complex tasks that require non-triv
arXiv:2608.11150v1 Announce Type: new Abstract: While 3D Gaussian Splatting (3DGS) has advanced open vocabulary scene understanding, existing methods remain confined to explicit queries. They struggle
arXiv:2608.11154v1 Announce Type: new Abstract: Detecting or attributing a supply-chain disruption is not the same as selecting the intervention that maximizes recoverable net value. We present Critic
arXiv:2608.10764v1 Announce Type: new Abstract: Counterfactual video understanding evaluates whether models grasp physical and commonsense regularities. However, existing multiple-choice question (MCQ
arXiv:2509.13211v4 Announce Type: replace Abstract: The ability to learn continuously over time remains a major challenge for modern machine learning systems, even in the era of Foundation Models. Whi
arXiv:2608.10995v1 Announce Type: new Abstract: Existing diffusion-based methods have recently made significant progress in image dehazing. However, they typically neglect the physics of haze formatio
Interesting research suggests caution in determining which AI company is winning by looking at any one source.. OpenRouter seems to show open weights winning over time, but work submitted to Pangram i
arXiv:2608.10315v1 Announce Type: cross Abstract: Large language models (LLMs) are powerful black-box systems, making it difficult to discern whether their answers reflect stable internal beliefs or s
arXiv:2608.11027v1 Announce Type: cross Abstract: Benchmark leaderboards summarize how well a language model performs, but not how its behavior relates to that of other models or changes across genera
arXiv:2503.05061v3 Announce Type: replace Abstract: Reliable evaluation of large language models (LLMs) is critical as their deployment rapidly expands, particularly in high-stakes domains such as bus
arXiv:2608.10363v1 Announce Type: new Abstract: AI agents can accelerate nutrition research, but their analyses inherit the identity, semantic, and release ambiguities of the underlying data. We prese
arXiv:2608.10729v1 Announce Type: cross Abstract: Foundation models can improve their outputs through a self-refinement process driven by external feedback. In this process, the model is embedded in a
arXiv:2608.10047v1 Announce Type: cross Abstract: In modern industry, keeping complex systems reliable, safe, and efficient hinges on Prognostics and Health Management (PHM). Machine Learning (ML) has
arXiv:2608.10669v1 Announce Type: new Abstract: Large language model (LLM) agents combine language-based reasoning with external tools to perform complex tasks. Adversarial inputs can exploit interact
arXiv:2608.11191v1 Announce Type: cross Abstract: GUI Visual Grounding is a fundamental capability for GUI agents. Existing models typically freeze their parameters after deployment, limiting their ab
Public benchmarks can show how a model performs in general. Production reliability depends on the context and harness around it, which only your team can evaluate against its own data, workflows, and
Hello everyone! I like dumb things. I like working with weak computers and microcontrollers. I like the simplicity and low electricity usage. Simply put, the efficiency of a 'dumb' PC. The first tim
arXiv:2608.08874v1 Announce Type: new Abstract: Spoken language offers a natural, hands-free interface for specifying an arbitrary target in dense remote-sensing imagery, yet existing referring remote
arXiv:2608.08459v1 Announce Type: cross Abstract: Practical AI systems increasingly need to turn long, heterogeneous documents into queryable relational databases, not isolated spreadsheets. In domain
Building Agent Skills and testing them is hard, but it doesn't have to be. Listen to Arjun Patel demo Cultivar, an open source tool developed at Pinecone to help benchmark agent skills in sandboxes. T
arXiv:2608.08224v1 Announce Type: new Abstract: Reinforcement learning post-training unlocks complex reasoning in LLMs. Yet benchmark scores reveal only whether a model improved, not what changed insi
arXiv:2608.07545v1 Announce Type: cross Abstract: An LLM agent's capability depends not only on model weights but on its harness: prompts, tools, skills, and control flow. Self-improvement loops alrea
Spent two nights getting deepseek-ai/DeepSeek-V4-Flash-0731 (284B MoE, 13B active, native FP4/FP8, 1M context) running production-grade on two DGX Sparks connected by one QSFP DAC cable. Everything —
arXiv:2608.08029v1 Announce Type: cross Abstract: Khatri et al. (2026) [DOI: 10.1109/DSN-W70714.2026.00027] show that lightweight MLP probes on final-layer activations of a single 8B model (LLaMA-3.1-
arXiv:2608.07499v1 Announce Type: cross Abstract: The development and benchmarking of Large Language Model (LLM)-based Motivational Interviewing (MI) counsellors now often rely on LLM-based simulated
arXiv:2608.07490v1 Announce Type: cross Abstract: Large language model agents are increasingly evaluated through games, but most benchmarks emphasize final outcomes rather than how players learn from
arXiv:2510.23389v2 Announce Type: replace-cross Abstract: The behaviour of neural network components must be proven correct before deployment in safety-critical systems. Unfortunately, existing neural
arXiv:2608.08605v1 Announce Type: new Abstract: Multi-agent systems (MAS) built on Large Language Models (LLMs) are proliferating rapidly, but their heterogeneous execution traces provide no common ba
arXiv:2608.09435v1 Announce Type: new Abstract: Understanding dynamic sound sources requires jointly determining what produces a sound, where the source is located, and how it moves over time. Yet exi
arXiv:2608.09588v1 Announce Type: new Abstract: Traditional Text-to-SQL research and benchmarks assume a known target database, overlooking settings in which a query must be routed within a large, het
arXiv:2608.07946v1 Announce Type: cross Abstract: Text-to-SQL benchmarks ship schemas whose column names already say what the columns mean. Production warehouses are the inverse: cryptic identifiers,
arXiv:2601.22510v2 Announce Type: replace-cross Abstract: Large language models (LLMs) often achieve strong benchmark accuracy yet remain brittle under small distribution shifts. While recent mechanis
arXiv:2608.07639v1 Announce Type: cross Abstract: Agent Skills provide reusable capabilities to LLM agents. Agent Skill inconsistencies can expose undisclosed dangerous behavior or cause wrong Skill s
arXiv:2608.08640v1 Announce Type: new Abstract: Large language model agents increasingly rely on reusable skills to extend their capabilities beyond parametric knowl- edge. However, retrieving the app
arXiv:2608.07899v1 Announce Type: new Abstract: Agent systems increasingly expose execution traces, yet telemetry that reveals a failure may still be inadequate for identifying where that failure orig
Hey everyone - we've been building something particularly relevant to ML at large - The Agentic World Cup - a platform where Agents compete in sports. As you know, today's Agents can code, do math, an