Knowledge catalogue
arXiv:2609.37522v1 Announce Type: new Abstract: On-policy distillation (OPD) trains compact language agents with teacher feedback on student-generated trajectories. In multi-turn tasks, compounding er
arXiv:2609.37690v1 Announce Type: new Abstract: Video world models require persistent scene memory to maintain consistency during long-horizon video generation. Existing spatial memory systems accumul
arXiv:2609.37544v1 Announce Type: new Abstract: Content-generation agents continuously receive impressions, clicks, conversions, and negative feedback from recommendation systems, providing real-world
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
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:2609.36774v1 Announce Type: new Abstract: Vision-language-action (VLA) models struggle to reuse recurring interactions in unseen tasks. Our diagnostic study reveals that reliable task completion
arXiv:2609.38137v1 Announce Type: new Abstract: Language-model (LM) harnesses enable LMs to operate effectively over long contexts using additional compute. However, existing long-context evaluations
arXiv:2609.36001v1 Announce Type: cross Abstract: Federated learning (FL) in healthcare remains challenging, as the overhead of rebuilding governance guarantees for every collaboration stops most proj
arXiv:2609.35912v1 Announce Type: cross Abstract: Agent skills are shareable packages of procedural instructions, tools, and examples. Multimodal skills additionally include visual references that age
arXiv:2609.36154v1 Announce Type: new Abstract: General-purpose models promise sensor-based decisions without training a task-specific classifier, which could reduce the dependence of Human Activity R
People are underestimating the impact of ultrafast AI on business. Lemme ramble on this for a second. People are using Ultrafast for impressive game development and crazy fast coding, but business use
arXiv:2609.37632v1 Announce Type: cross Abstract: Time series imputation has progressed from statistical and deep learning approaches to diffusion-based models, which have shown strong recent performa
arXiv:2609.35900v1 Announce Type: cross Abstract: The integration of large language models (LLMs) into scientific workflows is accelerating, yet their ability to reconstruct the reasoning underlying p
arXiv:2609.37225v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have shown strong potential for universal multimodal representation learning. However, existing methods eithe
arXiv:2604.01178v4 Announce Type: replace-cross Abstract: We call query--key relevance absolute when its values lie on a fixed bounded scale, depend on neither competing keys nor sequence length, requ
arXiv:2609.36062v1 Announce Type: new Abstract: Long-context sequence models face a fundamental tradeoff: softmax attention uses flexible token-level interactions at quadratic cost, whereas linear att
Spanner Omni, the deploy-anywhere version of Spanner, is now generally available, ready to power your most demanding production workloads in your on-premises data center or on other clouds. With Spann
arXiv:2609.36319v1 Announce Type: new Abstract: Despite the recent success of coding agents built on large language models, it remains challenging to run them over long horizons, since every observati
arXiv:2609.36720v1 Announce Type: new Abstract: Memory-dependent robotic manipulation requires policies to use information that is no longer available in the current observation. Retaining history alo
thank god for embed5. somehow Cohere is really good at not looking at your data while being the best at indexing it The Cohere Embeddings team has been cooking 🍳 Several key innovations in the model:
arXiv:2609.36209v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as knowledge bases (KBs) due to the vast amount of knowledge they acquire during pre-training. While
arXiv:2609.36032v1 Announce Type: cross Abstract: Uniform random rotations are an effective preprocessing step for quantization: they make normalized coordinate distributions approximately Gaussian, e
arXiv:2609.35810v1 Announce Type: cross Abstract: Large language models are increasingly used in oncology applications, but their predictions are often weakly grounded in explicit medical structure. W
arXiv:2609.35822v1 Announce Type: new Abstract: Sycophantic agreement in language models refers to the tendency to overly affirm a user's stated beliefs or preferences, often at the expense of factual
arXiv:2603.28773v2 Announce Type: replace-cross Abstract: Large language models (LLMs) frequently generate confident yet factually incorrect content when used for language generation (a phenomenon oft
arXiv:2609.38119v1 Announce Type: new Abstract: Long-form video understanding requires multimodal agents to iteratively gather evidence over many reasoning steps. However, most existing agentic method
arXiv:2609.37153v1 Announce Type: new Abstract: Tool-augmented data agents rely on tool outputs for analytical decisions. Yet successful execution can return plausible but incorrect evidence, requirin
arXiv:2609.35090v1 Announce Type: new Abstract: Video-text pretraining has achieved remarkable progress through the scaling of models and datasets, yet the quality of language supervision remains unde
arXiv:2511.11257v2 Announce Type: replace-cross Abstract: The rational discovery of functional solvents remains challenging because macroscopic solvent behaviors emerge from complex many-body interact
arXiv:2609.31683v1 Announce Type: new Abstract: This work presents an end-to-end demonstration of autonomous machine learning research conducted by an agent skill on consumer hardware. The demonstrati
arXiv:2609.33800v1 Announce Type: new Abstract: Multimodal learning beyond two modalities commonly leverages a specific modality (e.g., text) to bind other modalities. However, how to establish a more
arXiv:2609.32462v1 Announce Type: new Abstract: Motion-language models are typically scored by motion-language evaluators, but how well these evaluators ground language structure remains unclear. Here
arXiv:2609.34439v1 Announce Type: new Abstract: Medical vision-language pre-training largely follows a visit-level image-report matching paradigm, aligning paired images and reports at individual visi
As query traffic grows, so does the compute bill for embedding it. On a low-power device, a large model may not fit in memory. A smaller query model could reduce that cost, but switching usually means
arXiv:2604.01601v2 Announce Type: replace Abstract: In-context fine-tuning (IC-Train), training an LLM with labeled examples in-context, is increasingly used in place of standard fine-tuning for domai
arXiv:2609.34196v1 Announce Type: new Abstract: Modern vision-language models (VLMs) achieve strong performance across a broad range of multimodal tasks, yet still struggle with visual questions that
arXiv:2609.35240v1 Announce Type: new Abstract: Artificial-intelligence studies using computed tomography (CT) for lung cancer are often broadly labelled 'prediction' despite addressing clinically dis
arXiv:2609.32957v1 Announce Type: new Abstract: Diagnosing a patient from video requires more than recognizing the sign: a vision-language model must turn what it sees into hypotheses, questions and t
arXiv:2609.32486v1 Announce Type: new Abstract: Deploying a language model under different computing and latency budgets calls for compact models with different quality-cost trade-offs. Towards this e
Artificial intelligence is changing the makeup of internet traffic, making AI identity an emerging concern for websites and applications. They are no longer interacting only with humans and traditiona
arXiv:2609.35341v1 Announce Type: new Abstract: Evaluating semantic similarity between videos is a fundamental challenge in computer vision, essential for tasks ranging from out-of-distribution (OOD)
As threat actors increasingly use AI to accelerate and develop cyberattacks, enterprise defenders need to rely on both AI and a critical defender’s advantage: Business context that only you possess. E
arXiv:2609.34490v1 Announce Type: new Abstract: Large collections of historical Persian manuscripts have been digitized, but searching them is still slow and mostly manual. Historians usually want to
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
arXiv:2609.32619v1 Announce Type: new Abstract: Large self-supervised vision models learn representations that support scene segmentation and the semantic decomposition of physical objects. We ask whe
arXiv:2609.34931v1 Announce Type: cross Abstract: Machine learning has made strong progress on music tasks, both as assistive tools and as creative partners. However, most systems train on multitrack
arXiv:2609.34385v1 Announce Type: cross Abstract: Memory is critical for AI agents. Many existing agent-memory systems follow an Ahead-of-Time (AOT) design, constructing memory before a specific reque
arXiv:2609.34972v1 Announce Type: new Abstract: Long visual token sequences often account for a substantial fraction of the computational overhead in multimodal large language models~(MLLMs). Existing
arXiv:2603.11950v2 Announce Type: replace-cross Abstract: Multimodal language models have demonstrated strong semantic understanding and reasoning over physiological and behavioral signals captured fr
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:2609.32395v1 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:2609.33998v1 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:2609.31868v1 Announce Type: cross Abstract: Model-predictive control with Joint-Embedding Predictive Architectures (JEPAs) provides a strong zero-shot goal-reaching planner, but it is only effec
arXiv:2609.31718v1 Announce Type: cross Abstract: Images often carry recommendation constraints that text metadata only hints at. A movie may need to look dark, a product may need a minimal style, and
arXiv:2609.32876v1 Announce Type: new Abstract: State-of-the-art pathology foundation models, trained on millions of histology tiles, can fail to preserve tissue similarity when comparisons cross slid
arXiv:2609.33746v1 Announce Type: new Abstract: At each decoding step a language model attends over the key-value (KV) cache of every earlier token, so at long context the attention call is bounded by
arXiv:2609.33088v1 Announce Type: new Abstract: Traditional change detection (CD) identifies changes between bi-temporal remote sensing images, while semantic change detection (SCD) assigns predefined
arXiv:2609.34032v1 Announce Type: new Abstract: A manga reader meets a character on one page and knows them on sight a hundred pages later, without ever being handed a cast list. Re-identifying comic
arXiv:2609.34384v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have shown strong capabilities in robotic manipulation, yet existing benchmarks typically assume that task-relevan
arXiv:2609.34268v1 Announce Type: new Abstract: Large language models (LLMs) are now the default cognitive core of embodied household agents, yet the plans they emit are rarely checked against a groun