Knowledge catalogue
arXiv:2610.01548v1 Announce Type: new Abstract: As the use of large language models (LLMs) expands, post-training has become increasingly important for adapting them to downstream tasks. However, obta
arXiv:2610.01969v1 Announce Type: new Abstract: Concept erasure aims to remove a target concept, such as a copyrighted style, a recognizable character, or unsafe content, from a pretrained text-to-ima
arXiv:2610.00823v1 Announce Type: new Abstract: We present a planning and control approach to reactively use hand contacts to stabilize a humanoid in low stability scenarios, where only using feet con
arXiv:2606.13607v3 Announce Type: replace Abstract: When large language models (LLMs) fail to generalize or make content-sensitive errors in reasoning, it is often taken as evidence that LLMs are not
arXiv:2610.01184v1 Announce Type: cross Abstract: Remote multimodal models offer strong numerical reasoning capabilities over charts and speech, but sending private inputs risks exposing sensitive con
arXiv:2610.00558v1 Announce Type: new Abstract: While Mixture-of-Experts (MoE) models effectively scale model capacity through sparse activation, their deployment is often bottlenecked by prohibitive
arXiv:2610.01725v1 Announce Type: new Abstract: Tabular foundation models achieve state-of-the-art performance on single-table tasks without any training. Recent work suggests that they are also well-
arXiv:2610.00330v1 Announce Type: cross Abstract: Long-term object search requires learning where objects usually appear from repeated but uneven observations of a changing environment. We formulate r
arXiv:2502.14994v2 Announce Type: replace Abstract: The rapid advancement of AI-generated video poses challenges to digital authenticity and security. Current detection methods, often trained on speci
arXiv:2610.01544v1 Announce Type: new Abstract: Existing image forgery detectors often suffer from generalization to unseen manipulation methods due to the limited ability to capture transferable fore
arXiv:2610.00586v1 Announce Type: cross Abstract: Activation memory, not compute, limits CNN inference on constrained hardware such as microcontrollers. Direct in-place convolution removes the dual-bu
arXiv:2610.00964v1 Announce Type: cross Abstract: For small merchant businesses (SMBs) whose catalogs fit within a long-context LLM, full-catalog prompting offers a compelling alternative to multi-sta
arXiv:2602.08889v2 Announce Type: replace Abstract: Quantitative risk assessment relies on structured expert elicitation to estimate unobservable properties. The Delphi method produces calibrated, aud
arXiv:2610.02202v1 Announce Type: new Abstract: What makes great scientists great? Even as AI systems start to make progress on open problems, scientists remain far ahead of them at sensing which prio
arXiv:2610.01827v1 Announce Type: new Abstract: Modern computational methods can now propose candidate molecules, materials, and other scientific designs at an unprecedented scale, creating a validati
arXiv:2610.00031v1 Announce Type: new Abstract: Street-view imagery is increasingly used to infer urban attributes, but predictive accuracy alone does not reveal how much a photograph contributes beyo
arXiv:2610.01892v1 Announce Type: cross Abstract: Multimodal agents commonly generate free-form reasoning before each action. For small models, limited model capacity can result in lengthy reasoning t
arXiv:2610.01205v1 Announce Type: new Abstract: Objective assessment of microsurgical technical skill is essential for competency-based training and quality assurance, yet existing video-based approac
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,
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:2610.00207v1 Announce Type: cross Abstract: Due to limited support for intra-tensor heterogeneous precision in conventional accelerators, neural network quantization remains largely restricted t
arXiv:2610.00936v1 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:2610.01799v1 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: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:2610.00691v1 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:2610.00613v1 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: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:2610.00003v1 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:2610.00907v1 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: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: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
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:2610.00050v1 Announce Type: cross Abstract: Kolmogorov-Arnold Networks (KANs) represent a paradigmatic shift in deep learning by replacing fixed node activations with learnable univariate functi
arXiv:2610.01542v1 Announce Type: new Abstract: Cerebral microbleeds (CMBs) and cortical superficial siderosis (cSS) are imaging markers of cerebral small vessel disease, but their automated segmentat
arXiv:2610.00132v1 Announce Type: cross Abstract: Persistent AI agents revise beliefs, consolidate memory, and replace execution substrates. Similar successor states can accompany differently authoriz
arXiv:2610.00054v1 Announce Type: cross Abstract: Reading an LLM judge's verdict from the logits of its first generated token is cheap, requires no generation, and is exactly what constrained decoding
arXiv:2610.01768v1 Announce Type: cross Abstract: With the increasing capabilities of Large-Language-Models (LLMs) and LLM-based agents, users are increasingly using them to solve everyday problems, s
Something keeps happening in frontier AI, and the explanation we are given is always one size larger than the event. An OpenAI research model, running in a supposedly offline training environment, hit
arXiv:2610.00251v1 Announce Type: new Abstract: Memorization audits of generative models read similarity scores against thresholds, with no null distribution, and the conclusions they support can be w
arXiv:2610.00332v1 Announce Type: cross Abstract: Distilling the reasoning capabilities of large language models (LLMs) into smaller students is a central challenge for efficient deployment. Current a
arXiv:2610.00575v1 Announce Type: new Abstract: A common approach to world-model simulation for vision-language-action (VLA) systems is to predict future RGB observations and then re-encode them into
arXiv:2610.00309v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in privacy-critical domains (e.g., healthcare, finance, and government), but their propensity t
arXiv:2610.01763v1 Announce Type: new Abstract: Activation sparsity speeds up large language model (LLM) inference by setting unimportant activations to zero so that the corresponding computations can
arXiv:2610.00718v1 Announce Type: new Abstract: We present a teleoperation system that enables a single operator to perform construction tasks on a Unitree G1 humanoid, combining extended reality (XR)
arXiv:2610.01647v1 Announce Type: cross Abstract: In this article, we present our vision and recent advancements toward creating a decentralized system capable of learning from real-time data within b
arXiv:2610.00438v1 Announce Type: new Abstract: Humanoid whole-body manipulation has advanced rapidly, enabling policies to coordinate locomotion, posture, bimanual interaction, and dexterous hand mov
arXiv:2610.00895v1 Announce Type: cross Abstract: Foundation models remain vulnerable to spurious correlations and ``Clever Hans'' strategies. Explainable machine learning can find and remove such str
arXiv:2610.00590v1 Announce Type: cross Abstract: An autonomous cyber defender trained with reinforcement learning (RL) is typically tied to the network on which it was trained, limiting its ability t
arXiv:2610.01531v1 Announce Type: new Abstract: Vision-Language models (VLMs) are increasingly being explored in autonomous driving for tasks such as scene understanding, driving reasoning, decision-m
arXiv:2603.21152v4 Announce Type: replace-cross Abstract: Modern seismic networks resolve earthquake sequences in unprecedented detail, yet explaining how large earthquakes emerge from evolving fault
arXiv:2610.00822v1 Announce Type: new Abstract: Share the light, not the map. We study next-best-view selection for a team of robots, each of which builds its own 3D Gaussian Splatting map and keeps i
I have been building a somewhat unusual local inference machine around two Huawei Atlas 300I Duo cards. They are relatively inexpensive, passive, dual-accelerator PCIe cards with 96 GB of device memor
arXiv:2610.00102v1 Announce Type: new Abstract: Many machine learning (ML) applications rely on expert labels, and qualified experts may provide different but plausible interpretations of the same obs
arXiv:2610.01452v1 Announce Type: new Abstract: While state-of-the-art automated models for medical image segmentation achieve high mean performance, they frequently suffer from localized, catastrophi
arXiv:2610.01984v1 Announce Type: cross Abstract: Byte-level byte-pair encoding (BBPE) tokenizers are attractive for multilingual large language models (LLMs) because they cover all Unicode text. In U
arXiv:2610.02054v1 Announce Type: new Abstract: Vision-language-action models benefit from the understanding and reasoning capabilities of pretrained vision-language models, but action-only supervisio
arXiv:2610.00221v1 Announce Type: cross Abstract: What kind of data does a model need in order to learn? Coreset selection makes this question concrete: under a budget, keep the samples most useful fo
arXiv:2610.00972v1 Announce Type: new Abstract: As LLM agents undertake increasingly complex, long-horizon tasks, verifying their outputs becomes increasingly challenging. We study how verification ca