Knowledge catalogue
arXiv:2610.14155v1 Announce Type: cross Abstract: Reliable manipulation requires policies that generalize across tasks, layouts, and object interactions. Vision-language-action (VLA) models combine pr
arXiv:2610.14733v1 Announce Type: new Abstract: B-Human won multiple competitions in the Middle Division of the new Humanoid Soccer League in 2026. In addition to regular matches with three or five pl
chat: replace output string with parts (#30389) chat: replace output string with parts reserve first Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/5563975
server : escape the special tokens without std::regex (#30243) The d1-omni and kev prompts escape '<|name|>' in the request text with std::regex_replace. libstdc++ recurses for each char of the name,
webgpu: (Fix CI) fix mul_mat_id with duplicate expert ids (#30451) Fix mm-id of webgpu in the case of ids duplication formatting fix comments to avoid breaking up sentences in comments Website: https:
unicode : add opt-in NFC normalization for Unigram tokenizers (#30390) unicode : add opt-in NFC normalization for Unigram tokenizers Note: used help from Codex, Sol 6.1 Medium Fixing initial bot comme
vulkan: fix compile error (#30495) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/55839699 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm6
models: drop the t_embd expand of the embedding graphs (#30461) These graphs only produce embeddings, and build_pooling() already expands its output for every pooling type, so the expand at the end of
opencl: fix q8_0 dp4a mul_mat_id and mark PREC_F32 mul_mat_id unsupported for adreno (#30365) opencl: fix min handling for moe q8_0 dp4a GEMM Co-authored-by: Hongqiang Wang wangh@qti.qualcomm.com open
opencl: use buf+offset instead of subbuffer for adreno moe expert sort (#30418) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/55971785 macOS/iOS: macOS Ap
jinja : write floats in tojson as Python does (#30362) tojson printed floats through a C++ stream (6 significant digits, no '.0'), so 48.858844 became 48.8588 and 1.0 became 1 in tool definitions, too
cuda : use SIMT implicit GEMM conv2d on AMD without WMMA (#30325) cuda : use SIMT implicit GEMM conv2d on AMD without WMMA Assisted-by: Claude Opus cuda : update conv2d SIMT comment cuda : skip SIMT c
ggml : improve RPC tensor transfer logs (#30481) add rpc_log_format_size() and print byte counts in KiB/MiB/GiB across the RPC client, server and transport traces add rpc_log_format_tensor() and inclu
cuda, hip: GDN chunked kernel Ported-from: tetherto#257 Source-commit: 53f0027 Co-authored-by: Aman Gupta aman.gupta@tether.io fix older builds review fixes cuda: enable GDN MMA on tested Ampere and A
arXiv:2610.17615v1 Announce Type: cross Abstract: High-dimensional microscopy captures features across space, time, and spectrum, but complex backgrounds obscure signals. We present Background2Backgro
arXiv:2610.16048v1 Announce Type: new Abstract: Backward conformal prediction (BCP) fixes the size of a prediction set and estimates its miscoverage, but assumes calibration and test data are exchange
arXiv:2609.37140v1 Announce Type: cross Abstract: The conjugate gradient (CG) method is a classical iterative solver for sparse symmetric positive definite (SPD) linear systems, but its convergence st
Banger paper from Stanford, Together AI, and colleagues. Why is this an interesting paper? Today's LLM agents must write out every reasoning step as text before they can search, run code, or take acti
arXiv:2610.14997v1 Announce Type: new Abstract: While asynchronous execution enables VLA models to operate in real-time environments by predicting the next chunk during execution, it inevitably introd
arXiv:2610.16147v1 Announce Type: new Abstract: Dynamic sparse training (DST) aims to reduce training costs while maintaining accuracy. Existing DST methods mask out parameters but keep matrix dimensi
arXiv:2610.14017v1 Announce Type: cross Abstract: We propose Barycentric Anchored Search, a post-hoc weight-space procedure for improving fine-tuned vision models under distribution shift without addi
arXiv:2610.16892v1 Announce Type: new Abstract: Emotions are expressed on a continuum and are naturally described in the valence-arousal (VA) space. Existing VA-based image editors are typically train
arXiv:2610.15330v1 Announce Type: new Abstract: Accurate brain tumor segmentation from magnetic resonance imaging (MRI) is essential for diagnosis and treatment planning; however, manual delineation i
arXiv:2610.16330v1 Announce Type: new Abstract: Feed-forward transformer models have driven remarkable progress in 3D vision,yet their quadratic complexity renders them impractical for long video sequ
arXiv:1808.02932v5 Announce Type: replace-cross Abstract: In stochastic multi-armed bandits, rewards are generated by an unknown distribution; the world's reward uncertainty induces the exploration-ex
arXiv:2610.18306v1 Announce Type: new Abstract: We study Bayesian optimization of the Conditional Value-at-Risk (CVaR) of an expensive black-box function that depends on a decision and an environmenta
arXiv:2510.06439v2 Announce Type: replace Abstract: Hyperparameter tuning is a challenging problem especially when the system itself involves uncertainty. Due to noisy function evaluations, optimizati
arXiv:2610.18656v1 Announce Type: new Abstract: Language model systems repeatedly make test-time decisions by comparing similarity: they retrieve exemplars, rank candidates, and revise responses. Yet
arXiv:2610.16745v1 Announce Type: new Abstract: Attention sinks are usually studied after they have formed. We ask whether a measurable hidden-state change appears beforehand and whether changing that
arXiv:2610.14551v1 Announce Type: new Abstract: In multi-robot manipulation, an action's value depends on how teammates respond. We present method{} (Cooperative Action--Response Belief Estimation), a
// Behavioral Self-Rewarding for SWE agents // It's standard practice to train SWE agents on binary test rewards. This paper shows the problem with that. When every trajectory in a group passes, or ev
arXiv:2610.16322v1 Announce Type: new Abstract: Discovering behavioral patterns in open-ended games is challenging due to the lack of clear objectives or ground-truth annotations. In this work, we ext
arXiv:2610.18548v1 Announce Type: new Abstract: Language and vision language models can support autonomous systems, but changing operating conditions may compromise the reliability of their semantic o
arXiv:2610.15046v1 Announce Type: cross Abstract: Beliefs in a Partially Observable Markov Decision Process (POMDP) are posterior distributions over the hidden state given the agent's history of actio
arXiv:2610.16696v1 Announce Type: new Abstract: Signal Temporal Logic (STL) specifies robot tasks with spatio-temporal requirements, and its robustness semantics allow planning by trajectory optimizat
arXiv:2610.17966v1 Announce Type: new Abstract: Long-context inference makes the key-value (KV) cache a major memory bottleneck for large language models. We propose BELT, a low-rank KV cache compress
arXiv:2610.15818v1 Announce Type: new Abstract: Modern cloud platforms generate high-dimensional, noisy telemetry from thousands of microservices. Unlike classical anomaly detection benchmarks, cloud
arXiv:2610.18381v1 Announce Type: new Abstract: Aerial mobile manipulation requires unmanned aerial vehicles (UAVs) to traverse heterogeneous environments such as indoor and outdoor domains, and conne
arXiv:2610.18161v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong zero-shot reasoning across diverse domains, but their potential for Human-Object Inter
arXiv:2610.17573v1 Announce Type: new Abstract: Self-supervised pretraining has expanded the pool of 3D medical foundation models, but published evaluations use different datasets, endpoints and fine-
Benchmarks are becoming the core competency of any company. Our company mission is to build the world’s best models for document processing. This also means that we have to build the world’s best benc
arXiv:2506.00482v2 Announce Type: replace Abstract: LLM benchmarks are often treated as coherent measurement units, yet they are heterogeneous collections of instances spanning diverse domains, skills
arXiv:2610.17963v1 Announce Type: new Abstract: Brick-and-mortar retailers face many different challenges that involve understanding thoroughly its products catalog and customer preferences. In partic
arXiv:2610.16863v1 Announce Type: cross Abstract: Organizations pairing a human and a machine on a task decide, often by default, which executes each instance and what happens when both do. We account
arXiv:2610.14024v1 Announce Type: new Abstract: Physics time-series data are central to fundamental discoveries involving dark matter, neutrinos, and gravitational waves. Machine learning has shown st
arXiv:2610.15159v1 Announce Type: new Abstract: Existing depth-compression methods for large language models (LLMs) score layers individually or group only adjacent or contiguous layers, implicitly as
arXiv:2610.15543v1 Announce Type: cross Abstract: We study federated learning from continuously arriving data: each client samples from its own distribution, these distributions drift over time, and t
arXiv:2610.14151v1 Announce Type: cross Abstract: Reliable probability estimates are important for the clinical interpretation of machine-learning classifiers, yet radiomics--image fusion models for r
arXiv:2610.14753v1 Announce Type: new Abstract: Versatile quadruped locomotion depends on a tight coupling between what the robot perceives and what its body can execute. Yet existing visual controlle
arXiv:2610.14152v1 Announce Type: cross Abstract: Gate coefficients describe how a fusion layer weights intermediate features, but they do not necessarily reflect the magnitude of branch contributions
arXiv:2607.01416v2 Announce Type: replace Abstract: Concept Bottleneck Models (CBMs) provide an intrinsically interpretable alternative to post-hoc explanations. However, existing CBMs often rely on p
arXiv:2610.18167v1 Announce Type: new Abstract: End-to-end autonomous driving has achieved remarkable progress by planning trajectories directly from raw sensor data. Yet the step from planning to con
arXiv:2610.16105v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) typically uses small rollout groups per prompt, where repeated sampling from the same policy can y
arXiv:2610.18390v1 Announce Type: cross Abstract: We investigate whether the past of an auxiliary time series provides predictive information about a target beyond that contained in the target's own h
arXiv:2610.17799v1 Announce Type: new Abstract: Online reinforcement learning (RL) enables driving policies to adapt to changing deployment conditions, but requires safe exploration throughout trainin
arXiv:2610.16074v1 Announce Type: cross Abstract: Co-circulating influenza, COVID-19, and respiratory syncytial virus (RSV) create a shared hospital-admission burden, because beds, staff, testing capa
arXiv:2610.17233v1 Announce Type: new Abstract: Contrastive vision-language (VL) pretraining in computational pathology has generally relied on curated image-caption datasets sourced from social media
arXiv:2610.18375v1 Announce Type: new Abstract: A learned representation is useful beyond its source task only if later tasks can make use of what the encoder has already learned. Source-task performa
arXiv:2610.18543v1 Announce Type: new Abstract: Foundation models are increasingly used as feature extractors for downstream tasks with limited data, typically through representations obtained from th
arXiv:2610.17802v1 Announce Type: cross Abstract: Robot manipulation has traditionally relied on end-effector-centric interactions. In contrast, humans routinely exploit whole-arm contacts to improve