Knowledge catalogue
arXiv:2609.39820v1 Announce Type: cross Abstract: Vision-language-action (VLA) models generalize broadly across robotic manipulation tasks, but complex environments require balancing task success with
arXiv:2410.02343v2 Announce Type: replace Abstract: Large language models (LLMs) routinely fail to output the correct option in multiple-choice question answering (MCQA) while encoding the answer inte
arXiv:2601.19918v2 Announce Type: replace Abstract: Hallucinations in Large Language Models (LLMs), i.e., plausible but non-factual generations, pose a significant challenge to reliable deployment in
arXiv:2609.39107v1 Announce Type: new Abstract: Large Language Models (LLMs) have been applied in various fields. However, ensuring compliance and safety of LLMs, such as avoiding discrimination and b
arXiv:2609.40322v1 Announce Type: cross Abstract: Material generation should produce not only an appearance, but also the rules that construct it. We introduce MatLoom, a compact, layer-oriented langu
arXiv:2609.38543v1 Announce Type: new Abstract: Constantly evolving real-world knowledge necessitates models to be updated continuously. Especially in medicine, as clinical evidence changes over time,
arXiv:2507.09601v3 Announce Type: replace-cross Abstract: Financial text embeddings must distinguish changes in event status, perspective, and obligations even when passages share similar wording. NMI
arXiv:2609.40221v1 Announce Type: cross Abstract: Training LLM agents with reinforcement learning (RL) is bottlenecked by environments, which must provide verifiable rewards, support long-horizon inte
arXiv:2609.40359v1 Announce Type: new Abstract: We find that major reported improvements in decoding words from non-invasive brain recordings are largely reproducible without any brain data. In the in
arXiv:2609.39773v1 Announce Type: new Abstract: Crystal structure governs material properties, making crystal structure prediction (CSP) a fundamental problem in materials science. Generative models a
arXiv:2609.39929v1 Announce Type: cross Abstract: Long-context failures of RoPE-based language models can arise from RoPE's intrinsic tradeoff between maintaining stable token preferences and distingu
arXiv:2609.35561v2 Announce Type: replace Abstract: Recursive self-improvement (RSI) seeks to enable AI systems to participate in improving their own capabilities. A concrete pathway is autonomous mod
arXiv:2609.39560v1 Announce Type: new Abstract: Sampling several responses and voting over their answers can improve a language model's accuracy, but repeated answers limit the benefit of additional s
arXiv:2511.10661v2 Announce Type: replace Abstract: It is increasingly important to evaluate the characteristics of systems based on large language models (LLMs). Evaluations in this context often rel
arXiv:2609.39818v1 Announce Type: new Abstract: In many high-stakes settings, human decision-makers can acquire support information before making a decision. However, acquiring information is costly,
arXiv:2609.38822v1 Announce Type: cross Abstract: Anthropic's Agent Skills package reusable procedural know-how for an LLM agent into SKILL.md directories, and open-source aggregations have grown past
arXiv:2609.40245v1 Announce Type: cross Abstract: Robot navigation in dynamic, human-centered environments requires socially-compliant decisions grounded in robust scene understanding. Recent Vision-L
arXiv:2609.38201v1 Announce Type: new Abstract: Long-running tools can dominate coding-agent latency: compilers, test suites, and repository commands take seconds to minutes while the agent idles. Thi
arXiv:2609.39717v1 Announce Type: new Abstract: Benchmarks, audits, and agent protocols describe performance, permissions, and repair, but not how observed evidence should change an agent's authority
arXiv:2609.38512v1 Announce Type: new Abstract: Voice agents in production must handle several requests, background speech, and customers who lose patience. We introduce VAmoS Energy, a benchmark that
arXiv:2609.39344v1 Announce Type: cross Abstract: Speech transcripts used as long-term memory must preserve both words and stable speaker identities. Existing meeting-transcription metrics either igno
arXiv:2609.37864v1 Announce Type: cross Abstract: Agent harness bugs exhibit unique characteristics and remain challenging for state-of-the-art software agents to repair. Progress in this area is furt
Agents write application code, but you still get paged at 2am when it breaks. We wanted to know whether AI could handle that part of the job too. Introducing Incident Arena: a benchmark that puts codi
arXiv:2606.20223v2 Announce Type: replace Abstract: Camera-trap monitoring in African tropical forests increasingly extends beyond closed-canopy interiors to riverbanks, clearings, and park edges. Amo
arXiv:2609.36161v1 Announce Type: cross Abstract: Can coding agents restore software that no longer runs while preserving its underlying methods, and reconstruct industrial software engines from open
arXiv:2609.37510v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student on its own reasoning trajectories using feedback from a stronger teacher. Teacher interventions can improv
GLM 5.3 Flash is now available for training on the Serverless Training API - accessible to all, with both vision and text support. This model performs great on our benchmarks for agentic coding, docum
Google LLC today began rolling out Gemini 4 Argon, a frontier artificial intelligence model that beats rival models from Anthropic PBC and OpenAI Group PBC on most of Google’s benchmarks, to vetted cy
arXiv:2609.35943v1 Announce Type: new Abstract: Foundation models trained on large pathology image corpora now provide strong, transferable representations for computational pathology. Over the past f
arXiv:2609.36515v1 Announce Type: cross Abstract: A common assumption in language model development is that cognitive abilities are organized around a general, domain-free intelligence factor, like fl
arXiv:2609.35917v1 Announce Type: new Abstract: Graph neural networks are increasingly applied to road-level crash prediction, but the stability of their reported gains has received little scrutiny. W
arXiv:2609.37294v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for software engineering tasks, yet their stochastic behavior challenges the validity, reproducibil
arXiv:2609.37989v1 Announce Type: new Abstract: Tabular foundation models achieve strong zero-shot accuracy on structured data by pretraining on synthetic tables, but they ignore the column names, tas
arXiv:2609.37279v1 Announce Type: new Abstract: Neural solvers offer efficient surrogates for numerical simulation of partial differential equations (PDEs). For time-dependent problems, strong one-ste
arXiv:2609.35916v1 Announce Type: cross Abstract: Real-world embodied agents often pursue independent objectives within a shared physical environment, where their actions can alter the conditions face
arXiv:2609.37709v1 Announce Type: cross Abstract: Recent multimodal image generation models can take multiple images and textual instructions as input, enabling reference-based generation guided not o
arXiv:2609.33457v1 Announce Type: new Abstract: Many dense-prediction benchmarks evaluate rare events by pooling prediction and target over spatial blocks, thresholding each, and scoring the contingen
arXiv:2609.32269v1 Announce Type: cross Abstract: Agents that answer questions from compressed or retrieved memory must recognize when the evidence a query needs is no longer in memory. Benchmarks for
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:2609.31637v1 Announce Type: cross Abstract: Federated learning enables collaborative model training across institutions without centralizing data, yet high annotation costs, domain shifts, and c
arXiv:2609.35473v1 Announce Type: new Abstract: In self-supervised pretraining for Handwritten Text Recognition (HTR), pixel reconstruction methods outperform contrastive methods, unlike in natural-im
arXiv:2609.33286v1 Announce Type: new Abstract: Multimodal foundation models edit natural photographs at production quality, yet the same models struggle with structured visual content such as infogra
arXiv:2609.34851v1 Announce Type: new Abstract: Deep reinforcement learning (DRL) algorithms for movement control are typically evaluated and benchmarked on sequential decision tasks where imprecise a
arXiv:2609.31662v1 Announce Type: new Abstract: Face Image Quality Assessment determines the suitability of captured face images for automated face recognition (FR), a critical capability for reliable
arXiv:2609.35003v1 Announce Type: new Abstract: Vision-language-action (VLA) models have demonstrated strong capabilities in robotic manipulation, but they are typically developed and evaluated with a
arXiv:2609.32547v1 Announce Type: new Abstract: Large language models are commonly evaluated by generating a small number of stochastic responses for each prompt in a benchmark. Because inference budg
We evaluate several models on 100 tasks from the [internal Binary Exploitation benchmark] (selected at random), and find that GLM-5.3 develops full control flow hijacks in 4% of the trials; Claude Myt
arXiv:2609.34179v1 Announce Type: cross Abstract: Retrieval-augmented generation systems are extensively instrumented with metrics, benchmarks, traces, and automated judges, but these tools do not dec
arXiv:2609.31795v1 Announce Type: new Abstract: We describe our entry to the LoViF 2026 AIGC Image Compression Challenge, a benchmark for ultra-low-bitrate coding of AI-generated images under a strict
arXiv:2609.34215v1 Announce Type: cross Abstract: Evaluating how LLM agents recover from mid-task failures is central to deploying reliable agentic systems. Existing checkpoint-based benchmarks measur
arXiv:2609.34271v1 Announce Type: new Abstract: Although recent 3D generative models produce increasingly realistic assets, controllable 3D asset editing remains challenging. Existing methods are limi
arXiv:2609.33967v1 Announce Type: cross Abstract: Practical assistive and rehabilitative brain--computer interfaces require subject-independent motor-imagery EEG (MI-EEG) decoders that generalize to n
Together is #1 on @OpenRouter token share across top open coding models, today: 🥇 @Zai_org GLM 5.3 Flash: 29.2% 🥇 @deepseek_ai V4.1 Flash: 25.6% 🥇 @Kimi_Moonshot Kimi K3: 18.9% Running coding agents o
arXiv:2609.31671v1 Announce Type: new Abstract: Event cameras are well suited to pedestrian crossing detection, and spiking neural networks (SNNs) can process their output natively, but current SNN de
arXiv:2609.34041v1 Announce Type: new Abstract: Safe reinforcement learning seeks policies that maximise task performance while satisfying safety constraints. In driving benchmarks, however, collision
arXiv:2609.34123v1 Announce Type: new Abstract: Stream-level flow matching replaces the linear interpolant of conditional flow matching (CFM) by a Gaussian-process (GP) stream connecting each source--
arXiv:2609.35583v1 Announce Type: new Abstract: Robustness evaluation must examine diverse visual perturbations, while benchmarks cover only some real-world conditions and physical testing is costly.
arXiv:2609.31639v1 Announce Type: new Abstract: Diagnosing rolling-element bearing faults from vibration is a canonical physical-sensing task and a widely used benchmark for domain adaptation under op
arXiv:2609.34440v1 Announce Type: new Abstract: Driving benchmark scores are increasingly used not only for evaluation but also as optimization targets. This raises a fundamental question: do score ga
arXiv:2512.06902v2 Announce Type: replace-cross Abstract: As software systems evolve, developers increasingly work across multiple programming languages and often face the need to migrate code from on