Knowledge catalogue
arXiv:2609.07008v1 Announce Type: new Abstract: Multi-head latent attention (MLA) exposes many logical query heads through one packed latent KV stream. This representation is memory efficient, but it
Reinforcement learning at @cognition's scale is a hard infrastructure problem. We are proud to be part of the stack behind it. Congrats to the team on SWE-2! Read more about how we think about RL at F
arXiv:2609.08115v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) pretraining relies on an auxiliary load-balancing loss (LBL) to drive per-expert utilization toward uniformity. Post-training i
arXiv:2609.09999v1 Announce Type: new Abstract: Terminology-aware translation asks for more than a correct translation: the output must use the exact terms a glossary prescribes. The standard recipe,
arXiv:2609.08515v1 Announce Type: cross Abstract: As Large Language Models (LLMs) are increasingly integrated into human society, aligning them with pluralistic social values has become a critical pri
Same weights. 50 of harness search. 3x on Terminal-Bench. We optimized the OpenCode harness for GPT-OSS-20B (high reasoning) with a meta-harness: an agent that reads failures, patches the harness, and
arXiv:2609.09716v1 Announce Type: new Abstract: Customers rely on specific product attributes to compare products and make purchasing decisions, but e-commerce catalogs are messy and unstructured, mak
arXiv:2609.08443v1 Announce Type: cross Abstract: Modeling long-term user behavior is central to sequential recommendation and billion-scale industrial recommender systems, yet production ranking mode
arXiv:2609.09832v1 Announce Type: new Abstract: Recent advances in high-resolution fluorescence and electron microscopy have enabled nanoscale imaging across increasingly large brain volumes, but the
arXiv:2609.06540v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in safety-critical applications, yet jailbreak attacks can conceal harmful intent through role-
arXiv:2609.09247v1 Announce Type: cross Abstract: Local heatwave hazard depends on fine-scale air temperature, but ground stations are sparse and reanalysis products such as ERA5 cannot resolve the te
arXiv:2609.10303v1 Announce Type: new Abstract: Face recognition (FR) is a widely used modality for biometric authentication, but conventional models rely on visible-spectrum imagery and degrade when
arXiv:2601.19275v2 Announce Type: replace-cross Abstract: Tactile memory, the ability to store and retrieve touch-based experience, is critical for contact-rich tasks such as key insertion under uncer
arXiv:2502.08221v2 Announce Type: replace Abstract: The growing demand for efficient semantic communication systems capable of managing diverse tasks and adapting to fluctuating channel conditions has
The new DeepSeek V4.1 Flash model is mindblowing - back on top of the open-source model leaderboard and extremely cheap. It has a lot of very smart ways to be efficient and highly capable so I made a
arXiv:2609.09094v1 Announce Type: new Abstract: Combining search with function approximation has driven major advances in game-playing programs, making self-play algorithms more competitive than ever.
arXiv:2602.01437v2 Announce Type: replace Abstract: The problem of corrupted data, missing features, or missing modalities continues to plague the modern machine learning landscape. To address this is
This model is insane at landing pages. I asked DeepSeek V4.1 Flash & Claude Fable 5 to build me a landing page for a movie theater. Fable cost $1.21 while V4.1 Flash cost 2.6 cents, making it more tha
arXiv:2609.10210v1 Announce Type: new Abstract: How many of a transformer's components decide a token? Counted by the absolute value of each unit's and channel's contribution to the logit, one predict
arXiv:2512.21043v2 Announce Type: replace Abstract: Regulating grasping force to reduce slippage during dynamic object interaction remains a fundamental challenge in robotic manipulation, especially w
arXiv:2609.06974v1 Announce Type: cross Abstract: Large language models achieve strong performance across diverse tasks, but deployment remains costly because of memory, latency, and energy demands. S
arXiv:2609.09275v1 Announce Type: cross Abstract: Decays of beauty and charm hadrons provide sensitive probes of physics beyond the standard model, including decays with invisible particles, in which
arXiv:2607.11258v2 Announce Type: replace Abstract: Tree search algorithms enable systematic exploration of the proof space in neural theorem proving. Existing LLM tree search libraries primarily targ
arXiv:2609.09417v1 Announce Type: new Abstract: Vision-language models (VLMs) show promise for agricultural classification, but zero-shot performance on disease, pest, damage, quality, and species ide
arXiv:2609.09985v1 Announce Type: new Abstract: Real-world video understanding requires integrating visual, audio, textual, and temporal evidence distributed across a video. Yet many pipelines use a f
arXiv:2609.06840v1 Announce Type: cross Abstract: Web Application Firewalls (WAFs) mainly rely on signatures to detect known attacks, which can leave gaps against modified or previously unseen payload
arXiv:2609.06715v1 Announce Type: new Abstract: The contemporary debate over machine consciousness begins from a concealed assumption: that the object called 'AI' already constitutes the kind of entit
arXiv:2609.09245v1 Announce Type: cross Abstract: Repeated-sampling evaluations increasingly extrapolate pass@k far beyond the number n of samples collected per problem. We show that, in the pooled/ra
arXiv:2609.05663v1 Announce Type: new Abstract: We present a continuous, population-scale measurement record of autonomous language-model trading agents operating in production across two systems with
arXiv:2609.10033v1 Announce Type: new Abstract: Learning-based motion planners pay at training what classical planners pay per query. Trained in world coordinates, they relearn the same motion at ever
arXiv:2609.10261v1 Announce Type: new Abstract: Multi-modal medical image segmentation leverages complementary diagnostic information, yet fusion can underperform single-modality baselines when spatia
arXiv:2609.07741v1 Announce Type: new Abstract: Persistent AI assistants are intended to extend human attention, memory, and coordination across changing digital and physical environments. To be truly
arXiv:2508.15754v2 Announce Type: replace-cross Abstract: Tool use is often assumed to monotonically improve reasoning, where external evidence is expected to help when relevant and be ignored when ir
arXiv:2601.03103v2 Announce Type: replace-cross Abstract: Humor preferences vary widely across individuals and cultures, complicating the evaluation of humor using large language models (LLMs). In thi
arXiv:2510.15047v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) as agents often fail to improve in new environments. We identify and characterize a failure mode we call explorat
arXiv:2609.07299v1 Announce Type: new Abstract: Learned world models typically assume that observations arrive synchronously, an abstraction inherited from simulators that return a complete state vect
arXiv:2609.06535v1 Announce Type: new Abstract: We introduce 3DHarnessBench, a benchmark that evaluates the agentic ability of frontier vision-language models (VLMs) to recover 3D geometry as Blender
arXiv:2609.05985v1 Announce Type: new Abstract: Robots that follow open-ended language instructions need to connect semantic intent to visual scene understanding, geometric feasibility, object states,
arXiv:2609.08230v1 Announce Type: new Abstract: Chunk-autoregressive video world models typically condition each generated chunk on one action. An action received during sampling must therefore wait f
arXiv:2609.06984v1 Announce Type: new Abstract: Atrial fibrillation (AF) is the most common cardiac arrhythmia and is associated with increased risks of stroke and heart failure. The growing availabil
arXiv:2609.07439v1 Announce Type: new Abstract: Automated fingermark identification is the foundation of forensic investigation, yet progress in the field is held back by fragmented, closed-source sol
arXiv:2609.07036v1 Announce Type: cross Abstract: We identify the Flow Moment, a reasoning pattern characterized by sustained, process-confirming verbalizations such as I'm doing, in contrast to the r
arXiv:2609.06161v1 Announce Type: new Abstract: Large language models (LLMs) have achieved remarkable progress, yet their massive storage and memory-bandwidth demands still hinder efficient deployment
arXiv:2609.09030v1 Announce Type: cross Abstract: Chain-of-thought reasoning provides a structured computation between a model's input and final answer. Yet it is often evaluated through endpoint accu
arXiv:2604.02007v3 Announce Type: replace Abstract: Building general-purpose reasoning models using reinforcement learning with verifiable rewards (RLVR) across diverse domains has been widely adopted
arXiv:2609.08806v1 Announce Type: new Abstract: Arm pose estimation enables applications in fitness, extended reality input, rehabilitation, and life logging. Prior smartwatch-based approaches rely on
arXiv:2607.10655v2 Announce Type: replace Abstract: Robotic foundation models still need task-specific fine-tuning before deployment, and the fine-tuned policies often break under modest changes in sc
arXiv:2609.07012v1 Announce Type: cross Abstract: Pushbroom satellite imaging couples limited spatial resolution with platform attitude instability. Platform jitter produces spatially varying motion b
arXiv:2609.06726v1 Announce Type: new Abstract: We present B2TFPose, a training-free zero-shot method for 6DoF pose estimation of unseen objects from RGB images. Using a single frozen DINOv3 vision tr
arXiv:2609.07600v1 Announce Type: new Abstract: Tree species recognition supports forest inventory and biodiversity monitoring but still depends on scarce taxonomic expertise. Bark is visible year-rou
arXiv:2609.08055v1 Announce Type: cross Abstract: Many scientific graphs attach several variables to each node, so a single scalar edge weight cannot describe direction-dependent interactions. We mode
arXiv:2609.05860v1 Announce Type: new Abstract: Neural operators that accept arbitrary meshes are often treated as geometry-general, but unseen domain topology changes both the invariant and decaying
arXiv:2609.07362v1 Announce Type: cross Abstract: Converting in-service reinforced-concrete (RC) building blueprints into simulation-ready models---structured frame representations that support determ
arXiv:2609.05881v1 Announce Type: cross Abstract: Developers increasingly run large language models locally by pulling quantized GGUF artifacts from public registries, yet nothing in the distribution
Omarchy is a keyboard-first Linux desktop built on Arch and Hyprland by David Heinemeier Hansson (DHH), and its production pipeline, packaging builds, PR review agents, and QA testing, now run on Digi
arXiv:2609.06931v1 Announce Type: new Abstract: Invasive coronary angiography (CAG) is the gold standard for diagnosing coronary artery disease, but interpretation varies substantially among observers
arXiv:2606.14518v2 Announce Type: replace Abstract: The removal of learned data from Machine Learning models through Machine Unlearning (MU) has been widely studied; however, there is no agreed-upon s
arXiv:2609.05702v1 Announce Type: cross Abstract: Quantum Machine Learning (QML) has shown rapid advances by utilizing quantum computing for machine learning tasks. Meanwhile, the privacy risks accomp
arXiv:2505.15215v4 Announce Type: replace-cross Abstract: Data fusion, the process of combining observational and experimental data, can enable the identification of causal effects that would otherwis
arXiv:2609.05821v1 Announce Type: cross Abstract: Vision-language models (VLMs) often answer new questions about recurring visual content, where reusing the key-value (KV) cache can avoid re-encoding