Knowledge catalogue
arXiv:2609.33812v1 Announce Type: cross Abstract: Repeated runs of the same coding agent are known to give different benchmark scores. We ask what that variation means for a team running an agent on i
arXiv:2609.33183v1 Announce Type: cross Abstract: Large Language Models (LLMs) suffer from temporal misalignment, often due to the contradictory nature of their training corpora. While current mitigat
If you’re an adult who now says Super Intelligence because that person said so, you are, in fact, not an adult at all. Trump: 'We're gonna be signing a document today renaming artificial intelligence,
arXiv:2609.35748v1 Announce Type: cross Abstract: Looped transformers have demonstrated promising parameter efficiency by reusing layers for latent computation. Prior studies compare looped and non-lo
ninfer, dwarfstar, Splash, llamAmpere, gufo, etc. We've all seen them popping up, great tok/s, people loving them. Forks of llama.cpp or another engine, or made from scratch. For better or worse, the
arXiv:2609.33286v1 Announce Type: new Abstract: Multimodal foundation models edit natural photographs at production quality, yet the same models struggle with structured visual content such as infogra
arXiv:2609.32660v1 Announce Type: new Abstract: Table images preserve structural information that are often lost in text serialization, and reasoning over them requires locating relevant rows, columns
Elizabeth Dias / New York Times: Interviews with Anthropic co-founder Christopher Olah and 20 religious and philosophical leaders about their summits to investigate consciousness in Claude — “To be cl
OpenAI announced the launch of **dots**, an always‑on agent system powered by the GPT‑6 Astra model. According to OpenAI, dots are “remarkably capable” agents designed to handle a wide range of tasks
arXiv:2609.33416v1 Announce Type: new Abstract: In this paper, a methodology to design fair graph convolutional neural networks (GCNs) is developed and tested over several application data sets. The g
arXiv:2609.32857v1 Announce Type: new Abstract: Predicting spatial gene expression from routine H&E histology offers a scalable route toward spatial molecular profiling. Recent work has pursued increa
arXiv:2609.33585v1 Announce Type: new Abstract: The rapid proliferation of highly realistic AI-Generated Content (AIGC) necessitates robust and interpretable detection mechanisms. However, existing de
arXiv:2609.35350v1 Announce Type: cross Abstract: While Large Reasoning Models (LRMs) excel at complex reasoning, alignment through reinforcement learning often induces systemic overconfidence. In pro
arXiv:2609.34024v1 Announce Type: cross Abstract: Jev is a non-generative 'System One' model that assigns probabilities to predefined answer options and cannot answer outside them. Its accuracy and ca
arXiv:2603.20984v2 Announce Type: replace Abstract: Gaussian process surrogates dominate constrained multi-objective optimization because they are effective in data-scarce regimes, but their cubic sca
arXiv:2609.35032v1 Announce Type: cross Abstract: In complex embodied visual reasoning scenarios, an agent often has only a limited field of view, and the evidence needed to answer a question may be d
arXiv:2609.33074v1 Announce Type: new Abstract: High-performance GPU kernels are essential to modern machine learning systems, yet automatically generating kernels that are both correct and efficient
arXiv:2609.34507v1 Announce Type: cross Abstract: Financial candlestick forecasting is fundamental to quantitative investment, yet it remains exceptionally challenging due to extremely low signal-to-n
arXiv:2609.32610v1 Announce Type: cross Abstract: Large language models represent context with a key-value (KV) cache. Caches are model-specific: for the same text, models with different architectures
arXiv:2609.35335v1 Announce Type: new Abstract: Machine learning task type identification is essential for constructing valid ML pipelines, yet in practice it is typically specified manually. We inves
arXiv:2609.33843v1 Announce Type: cross Abstract: The shipped Laya Typed-Decisions checkpoint, a 421M-parameter ModernBERT-large assessor that answers typed choice/noul/score questions over workflow s
arXiv:2609.34711v1 Announce Type: new Abstract: Learning local geometry enables graph neural networks (GNNs) to adapt how they compare and integrate neighborhood information. However, estimating geome
arXiv:2609.31662v1 Announce Type: new Abstract: Face Image Quality Assessment determines the suitability of captured face images for automated face recognition (FR), a critical capability for reliable
arXiv:2609.32272v1 Announce Type: cross Abstract: Multimodal tabular-image learning is gaining growing attention, yet it faces challenges due to tabular data unavailable at test time. A practical solu
arXiv:2609.35003v1 Announce Type: new Abstract: Vision-language-action (VLA) models have demonstrated strong capabilities in robotic manipulation, but they are typically developed and evaluated with a
arXiv:2609.34344v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a key paradigm for enhancing the reasoning of large language models, yet the high dimensionality of parameter upd
arXiv:2609.32785v1 Announce Type: cross Abstract: Domain incremental learning is essential for adapting ophthalmic deep learning models to sequential clinical domains while preserving diagnostic exper
arXiv:2601.06641v3 Announce Type: replace Abstract: Membership inference attacks (MIAs) pose a serious privacy threat in federated learning (FL). While MIAs have been extensively studied in standard F
arXiv:2609.34446v1 Announce Type: new Abstract: Generative models have found great success as data-driven methods of solving inverse problems. Two popular approaches work either by combining a pretrai
arXiv:2609.32103v1 Announce Type: new Abstract: Large language models can memorize private or harmful information, motivating machine unlearning methods that remove targeted knowledge while preserving
arXiv:2609.33521v1 Announce Type: new Abstract: Trust evaluation plays a critical role in cybersecurity by supporting risk mitigation and decision-making. A variety of trust evaluation methods have be
arXiv:2609.35427v1 Announce Type: new Abstract: Modern LLMs are increasingly capable as autonomous agents, but they follow sequential interaction cycles: read, think, reply or call tools, repeat. Many
arXiv:2609.34427v1 Announce Type: new Abstract: Scaling LLM-based optimization from textbook-scale instances to real-world, industrial tasks remains a critical open challenge. Existing approaches are
arXiv:2609.34493v1 Announce Type: new Abstract: Explicit residual connections of the form (x+f(x)), often combined with normalization layers, have become a standard strategy for training very deep neu
arXiv:2601.13556v2 Announce Type: replace Abstract: Simulated environments play an essential role in embodied AI, functionally analogous to test cases in software engineering. However, existing enviro
arXiv:2609.34630v1 Announce Type: new Abstract: Real-world AI systems must reason about objects that are no longer visible: an AR assistant guiding a user back to an object used earlier, a household r
arXiv:2609.35536v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) can explain deepfake verdicts in natural language, but such explanations are not necessarily visually grounded
arXiv:2609.34386v1 Announce Type: cross Abstract: On-policy distillation (OPD) uses teacher correction on student-generated responses. Full-vocabulary correction can provide important corrections even
arXiv:2609.34218v1 Announce Type: new Abstract: Looped language models separate computational depth from parameter count by repeatedly applying the same transformer block. Adapting these models requir
arXiv:2609.33306v1 Announce Type: new Abstract: Current Transformer-based tracking methods typically stack multiple Transformer blocks with separate parameters to model interactions between the target
arXiv:2609.33025v1 Announce Type: new Abstract: Low-rank matrix and tensor bandits exploit structured interactions but typically assume a known reward link. Recent single-index bandit methods accommod
arXiv:2609.34375v1 Announce Type: new Abstract: Compact JEPA world models enable efficient latent-space planning, but low-dimensional representation trained under reward-free self-supervision must enc
arXiv:2609.31898v1 Announce Type: cross Abstract: Humans rely on gaze, head movements, and visual cues to attend to speakers in noisy environments, yet auditory attention decoding (AAD) has been studi
arXiv:2609.34262v1 Announce Type: cross Abstract: Agentic benchmarks guide model selection and training. Yet an agent can pass a task without demonstrating the intended capability. Such outcomes const
arXiv:2601.06025v2 Announce Type: replace-cross Abstract: We study the discrete-to-continuum consistency of the training of shallow graph convolutional neural networks (GCNNs) on proximity graphs of s
arXiv:2609.35658v1 Announce Type: new Abstract: Real-world capture is heterogeneous: perspective, fisheye, and 360^irc panoramic images can coexist within a single reconstruction task, yet most feed-f
arXiv:2609.34077v1 Announce Type: new Abstract: Mixture-of-experts (MoE) language models often exceed the memory of a single GPU. Expert offloading keeps most experts in host memory and loads them on
arXiv:2609.32445v1 Announce Type: cross Abstract: Direct Preference Optimization (DPO) aligns language models by optimizing over sequence-level sums of token-wise implicit reward differences. However,
arXiv:2511.18038v2 Announce Type: replace-cross Abstract: Testing RESTful API is increasingly complicated but indispensable to quality assurance of cloud-native applications. This paper reports a mult
arXiv:2609.31705v1 Announce Type: new Abstract: Byte-Pair Encoding (BPE) constructs subword vocabularies through greedy pair merging, but conventional BPE requires the number of merges or target vocab
arXiv:2609.31640v1 Announce Type: new Abstract: Continual Learning Bench scores learning as short-horizon gain versus a reset baseline and finds naive full-context ICL strongest among the memories it
arXiv:2609.35515v1 Announce Type: cross Abstract: Scientific discovery requires not only recovering mathematical laws that describe observable behavior, but also identifying the mechanisms that genera
arXiv:2609.32395v1 Announce Type: cross Abstract: The KV cache of a transformer entangles every token's representation with its entire prefix: a passage encoded once cannot be reused under a different
arXiv:2609.35431v1 Announce Type: new Abstract: This paper studies low-altitude question answering (LAQA), in which distributed unmanned aerial vehicle (UAV) memories are aggregated at a ground server
arXiv:2609.32313v1 Announce Type: new Abstract: Memory lets an embodied agent reuse past experience, yet retaining useful information does not ensure that the agent can apply it when conditions change
arXiv:2609.33998v1 Announce Type: new Abstract: Frame selection is an important component of long-video question answering (VQA) with Multimodal Large Language Models (MLLMs). Existing frame-selection
arXiv:2609.32808v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) inherit massive activations from their text-only bases: spikes where a few fixed hidden channels receive values t
arXiv:2609.33246v1 Announce Type: new Abstract: Posterior sampling for reinforcement learning (PSRL) is one of the simplest and most effective exploration methods, but a basic question has remained op
arXiv:2609.33893v1 Announce Type: new Abstract: Large audio-language models (LALMs) produce fluent responses about audio but often hallucinate by making plausible yet ungrounded claims. Existing audio
arXiv:2609.32656v1 Announce Type: cross Abstract: Multivariate Time Series Forecasting (MTSF) models that mix information across channels assume that the past of one channel carries information about