Knowledge catalogue
arXiv:2610.02068v1 Announce Type: cross Abstract: How complex can the responses of a quantum device become as it runs longer with a fixed internal memory? We quantify this complexity through sequentia
arXiv:2610.00717v1 Announce Type: cross Abstract: Post-training compression of LLM attention is often formulated as independent matrix approximation, ignoring both the shared structure among attention
SETA got accepted to NeurIPS 2026! 🎉 We released the full training scripts for DeepSeek-V4-Flash, GLM-5.2 (LoRA), Inkling-Small, and Qwen3.8-27B, with both GRPO and PPO, alongside 4,500+ open-source,
Sharing some notes from OpenAI DevDay in parts. The first part matters, since it's on everyone's mind. How do you optimize for cost and performance? If you are building agentic applications today, the
arXiv:2610.01951v1 Announce Type: new Abstract: Top-two algorithms are simple and effective for fixed-confidence best-arm identification, but their sharp non-asymptotic behavior is still not well unde
arXiv:2610.00254v1 Announce Type: new Abstract: We characterize the regret attainable in online convex optimization when access to the feasible set is limited to an exact linear optimization oracle. T
arXiv:2610.00903v1 Announce Type: new Abstract: Test-time reinforcement learning (TTRL) adapts language models on unlabeled test problems using supervision derived from their own samples. This makes t
arXiv:2610.01509v1 Announce Type: new Abstract: An emerging hypothesis about reinforcement learning (RL) post-training of large language models (LLMs) is that it merely sharpens existing behaviors of
arXiv:2610.00838v1 Announce Type: cross Abstract: Agentic reinforcement learning (RL) trains a large language model (LLM) to act over long, multi-step interactions. However, a single localized error c
arXiv:2610.00207v1 Announce Type: cross Abstract: Due to limited support for intra-tensor heterogeneous precision in conventional accelerators, neural network quantization remains largely restricted t
arXiv:2610.01283v1 Announce Type: new Abstract: Reliable shelf monitoring is an important capability for retail automation, yet existing out-of-stock detection methods mainly operate in image space an
The results are in, no thinking / instruct mode for new models degrade performance more than on old models such as 3.6 vs 3.8, where 3.6 takes the lead on several coding benches in instruct mode. I wo
arXiv:2610.00936v1 Announce Type: new Abstract: With the global population rapidly aging, maintaining independence in Activities of Daily Living (ADLs), particularly bathing or showering, has become a
arXiv:2610.01962v1 Announce Type: cross Abstract: The ability of vision-language models (VLMs) to associate visual identities with biographical information creates a need for selective unlearning of p
arXiv:2610.00751v1 Announce Type: cross Abstract: Recent theoretical work identified fundamental properties of representation geometry that shape inference ability of deep neural networks. These inclu
arXiv:2610.00262v1 Announce Type: cross Abstract: Selective intent routing allows an assistant to act on reliable predictions while deferring uncertain requests. Standard confidence scores primarily r
arXiv:2610.02201v1 Announce Type: cross Abstract: High-resolution 3D generation increasingly relies on voxel latents and multi-stage pipelines that first predict active structure and then synthesize l
arXiv:2610.00523v1 Announce Type: new Abstract: Conformal prediction guarantees marginal coverage, but a single calibration threshold can still spread that coverage unevenly, over-covering easy region
arXiv:2610.01974v1 Announce Type: new Abstract: Simulation and experimental measurements provide complementary data for learning spatiotemporal physical systems, but standard simulation-to-experiment
arXiv:2610.01180v1 Announce Type: new Abstract: Despite the strong performance of Vision-Language Models (VLMs) on a wide range of visual question answering (VQA) tasks, these models consistently stru
arXiv:2610.02120v1 Announce Type: new Abstract: World action models (WAMs) combine robot action generation with future state prediction. Existing WAMs typically predict videos or learned visual latent
arXiv:2610.01799v1 Announce Type: new Abstract: Skill evolution offers a promising way to improve large language model agents without updating their parameters, but its use in formal theorem proving r
arXiv:2610.00704v1 Announce Type: new Abstract: Natural-language skills are textual procedural memories through which large language model (LLM) agents retain reusable task knowledge without updating
arXiv:2606.22676v2 Announce Type: replace Abstract: Refusal on a safety benchmark does not reveal how stable that behavior will remain after model updates. Benign downstream fine-tuning can weaken ref
arXiv:2610.01037v1 Announce Type: new Abstract: Optimizing merging coefficients for large language models can require many costly benchmark evaluations. We propose extbf{Simplex-Lattice Interpolation
arXiv:2610.01408v1 Announce Type: new Abstract: Trajectory crossing remains a critical bottleneck in Flow Matching (FM), and previous works typically view these crossings from a theoretical optimizati
arXiv:2610.00851v1 Announce Type: new Abstract: Open Set Recognition (OSR) aims to enable models to accurately classify known classes while rejecting samples from unseen classes. A key challenge in OS
arXiv:2610.02182v1 Announce Type: cross Abstract: Quasi-Newton (QN) methods have long been among the most effective methods for large-scale unconstrained convex optimization. Two obstacles have limite
arXiv:2610.01756v1 Announce Type: cross Abstract: Decentralized agent economies increasingly build a single task from protocols that were designed and secured separately. This creates a simple problem
arXiv:2610.01644v1 Announce Type: new Abstract: Autonomous underwater vehicles (AUVs) assisting human divers must continuously track not only the diver's 3D position but also their full-body orientati
arXiv:2610.00691v1 Announce Type: new Abstract: Recent joint audio-video generative models can synthesize realistic videos with synchronized sound, but typically generate audio as a single mixed track
arXiv:2610.00417v1 Announce Type: new Abstract: Repeated training on model-generated data can degrade later models. One possible response is to use provenance when deciding which generated examples to
Bloomberg: Sources: Broadcom's Wall Street syndicate is amassing 60B in AI chip financing to help Anthropic and others access chips and other key AI infrastructure — Broadcom Inc.'s Wall Street syndic
arXiv:2610.00017v1 Announce Type: cross Abstract: We present Spatial Lifting (SL), a novel methodology for dense prediction tasks. SL operates by lifting standard inputs, such as 2D images, into a hig
arXiv:2610.00613v1 Announce Type: new Abstract: Large language model (LLM) based agents are often criticized for lacking spatial understanding and mainly exploiting statistical text patterns. We inves
arXiv:2610.00805v1 Announce Type: cross Abstract: Editing a chest radiograph requires completing the requested change while preserving unrelated content. We study a latent diffusion editor with an ins
arXiv:2610.00395v1 Announce Type: new Abstract: Inference-time steering enables pretrained diffusion models to satisfy new constraints without full retraining. However, specificity-aware generation is
arXiv:2610.02023v1 Announce Type: new Abstract: While Large Language Models (LLMs) advance 3D indoor scene synthesis, current pipelines fail to retain user-specific preferences across sessions, making
arXiv:2610.02208v1 Announce Type: new Abstract: Sphere Encoder is an autoencoder that generates images by decoding random points from a high-dimensional latent sphere. We identify two limitations of t
arXiv:2610.01418v1 Announce Type: new Abstract: Spiking Neural Networks (SNNs) enable event-driven computation through biologically inspired dynamics at the neuronal scale, while Mixture-of-Experts (M
arXiv:2606.23595v2 Announce Type: replace Abstract: Language model reasoning can be substantially improved at test time via scaffolds that scale inference compute across different primitives -- sequen
arXiv:2610.00742v1 Announce Type: cross Abstract: Every protein has a unique stability landscape, but the physical consequences of mutation are governed by recurring biochemical constraints. We test w
arXiv:2610.00280v1 Announce Type: new Abstract: A world model learns to forecast how a physical system evolves from recorded trajectories, yet the systems it imitates obey physical laws that are neith
arXiv:2610.01302v1 Announce Type: new Abstract: Concept erasure suppresses a target concept while preserving behavior on unrelated inputs. Existing closed-form methods were designed for 2D image diffu
arXiv:2610.00003v1 Announce Type: cross Abstract: Vision models pretrained for frame-level appearance often struggle to infer hidden physical properties from motion. We study center-of-mass (CoM) loca
arXiv:2610.00377v1 Announce Type: new Abstract: Station-based weather forecasting supports daily life and economic activity, yet accurate forecasts require modeling complex spatial dependencies among
arXiv:2610.00907v1 Announce Type: cross Abstract: Relational foundation models (RFMs) are pretrained once on a collection of relational databases and prediction tasks, and then applied zero-shot to pr
arXiv:2303.00897v2 Announce Type: replace Abstract: Federated learning is a distributed learning framework that takes full advantage of private data samples kept on edge devices. In real-world federat
arXiv:2502.04892v2 Announce Type: replace Abstract: Learning robust representations from functional magnetic resonance imaging (fMRI) is fundamentally challenged by the temporal irregularity and noise
arXiv:2610.01889v1 Announce Type: new Abstract: Should low-precision transformer inference use stochastic rounding (SR) or round-to-nearest (RN)? The answer depends on where in the network you look. W
arXiv:2610.01456v1 Announce Type: new Abstract: Given a set of n points X in a metric space and an integer k, max-min diversification aims to select k points of X maximizing their minimum pairwise dis
arXiv:2610.00968v1 Announce Type: cross Abstract: Causal representation learning aims to discover robust features by exploiting the causal structure underlying data generation. Existing methods requir
arXiv:2503.16311v2 Announce Type: replace-cross Abstract: Masked modeling has emerged as a robust self-supervised learning framework. However, most methods rely on random masking, which disregards the
arXiv:2607.09086v2 Announce Type: replace Abstract: We present Subtoken Vision Transformer (SubViT), a selective image tokenization method for fine-grained visual recognition. Standard Vision Transfor
Super interesting paper from Meta Superintelligence Labs on controlling long agent runs. They use the same workers and same budget, and ProgramBench goes from 63.7% to 71.5% with GPT-5.5 when a dedica
arXiv:2610.01517v1 Announce Type: new Abstract: Text-driven human motion editing aims to realize a requested change while preserving compatible source content. Existing diffusion editors rely largely
arXiv:2610.01224v1 Announce Type: new Abstract: Latent world models plan by scoring candidate action sequences with distances in latent space. However, task success is judged by physical quantities, w
arXiv:2610.01388v1 Announce Type: cross Abstract: We present a method for learning binaural sound localization using egomotion as a supervisory signal. Over the course of a video, the cameras directio
arXiv:2610.01381v1 Announce Type: cross Abstract: Peptide sequence governs both the structures formed through supramolecular assembly and the dynamics by which they emerge, but predicting either requi
arXiv:2610.02114v1 Announce Type: new Abstract: Existing genome-wide association studies (GWAS) of brain imaging provide predefined or deep-learning-derived imaging phenotypes, yet these phenotypes co