Select, Label, Evaluate: Active Testing in NLP
arXiv:2603.21840v2 Announce Type: replace Abstract: Human annotation cost and time remain significant bottlenecks in Natural Language Processing (NLP), with test data annotation being particularly exp
Knowledge catalogue
arXiv:2603.21840v2 Announce Type: replace Abstract: Human annotation cost and time remain significant bottlenecks in Natural Language Processing (NLP), with test data annotation being particularly exp
arXiv:2608.27666v1 Announce Type: cross Abstract: Semantic watermarks tie the mark to sentence meaning rather than token choices, promising robustness to content-preserving edits. However, the detecto
Interesting new paper from Alexia Jolicoeur-Martineau (of Tiny Recursive Model fame) and collaborators. They seem to be able to replace quadratic attention with sliding window attention + attention si
arXiv:2511.14684v2 Announce Type: replace Abstract: Large language models (LLMs) often make reasoning errors when solving mathematical problems, and how to automatically detect and correct these error
arXiv:2608.28270v1 Announce Type: new Abstract: We present a real-time semantic navigation framework for Unmanned Aerial Vehicles (UAVs) focused on improving time efficiency in the Object Goal Navigat
arXiv:2608.28229v1 Announce Type: cross Abstract: Grammar-constrained decoding helps large language models produce syntactically valid structured outputs, such as code, JSON, and SQL. For context-free
arXiv:2608.28467v1 Announce Type: new Abstract: Persona-based dialogue systems are usually conditioned on speaker biography, but dialogues involve at least two participants, and who has access to whos
arXiv:2608.27467v1 Announce Type: new Abstract: We describe the UIC-AIHealth4All system for ArchEHR-QA 2026, a shared task on grounded question answering from electronic health records. We participate
arXiv:2608.28306v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) improves reasoning by training a problem-only student on its own rollouts using dense token-level supervision from
arXiv:2608.28518v1 Announce Type: cross Abstract: We investigate whether automatic speech recognition (ASR) errors in user input can lead to unsafe outputs from Embodied AI (EAI) models. We find that
Anthropic recommends that users clear or update their **CLAUDE.md** file after each new model release, ensuring the documentation reflects the latest changes. The message includes an informal comment
I put together a technical guide for installing AutoGPT from source, with a focus on using local models instead of OpenAI. It includes Docker Compose files, environment variables, and how to point the
// Memory is what breaks long-horizon agents // It's undeniable how important memory/recall is for long-horizon tasks. If you are building for long-horizon tasks, this is a great read. (bookmark it) T
Hey! I forked NInfer (a from-scratch C++20/CUDA inference engine for Qwen models) and added two things: tensor-parallel across two GPUs, and YaRN ×4 rope scaling. Together they let Qwen3.8-27B NVFP4 r
One time, a young ML researcher asked Master Ilya: 'Teacher, according to the formulas, if I use the same seed and same prompt with the same weights, I will get the same results. Is my math right?' Ma
This base model is only 43m parameters trained on 3m arXiv abstracts. We plan to continue pre-training and post training. If you create fine-tuning datasets or if you know of any datasets that can hel
arXiv:2608.26506v1 Announce Type: cross Abstract: Model merging enables combining multiple fine-tuned models without additional training, but its safety implications remain poorly understood. Prior wo
arXiv:2608.26807v1 Announce Type: cross Abstract: Travel planning agents assist users in generating personalized travel plans by modeling their individual preferences. Existing agents either rely on e
arXiv:2508.11017v3 Announce Type: replace-cross Abstract: Large language models (LLMs) struggle with cross-lingual knowledge transfer: they sometimes hallucinate when asked in one language about facts
arXiv:2608.27334v1 Announce Type: new Abstract: Industrial sites contain large volumes of read-only telemetry, but few benchmarks specify how to compile these records into executable multi-turn agent
arXiv:2608.27038v1 Announce Type: new Abstract: Although batch prompting makes large language model inference more efficient by processing multiple instances simultaneously, it suffers from unpredicta
arXiv:2608.26899v1 Announce Type: new Abstract: Automated candidate-job matching systems are increasingly classified as high-risk AI under emerging regulation, yet auditing them for demographic bias i
arXiv:2604.14586v4 Announce Type: replace-cross Abstract: The rapid expansion of gaming industry requires advanced recommender systems tailored to its dynamic landscape. Existing Graph Neural Network
arXiv:2608.27455v1 Announce Type: new Abstract: Recent advances in inference-time scaling have significantly improved the reasoning performance of large language models (LLMs). However, these methods
arXiv:2608.26750v1 Announce Type: new Abstract: Data lakes rely on metadata to remain usable, yet this meta data is often limited or weakly informative for column relationship discovery, especially in
arXiv:2607.15439v2 Announce Type: replace Abstract: Our previous ARC-AGI-3 agent bundled executable world modeling, prompted simplification, and exact replay verification, leaving their individual con
arXiv:2509.03345v3 Announce Type: replace Abstract: Non-deductive reasoning, encompassing inductive and abductive reasoning, is essential in addressing complex real-world questions. One key feature of
arXiv:2608.26576v1 Announce Type: new Abstract: When researchers compare multilingual models for probing, interpretability, or cross-lingual transfer, they often align embedding spaces and assume that
arXiv:2608.26546v1 Announce Type: new Abstract: Autonomous agents are increasingly adopted to complete complex, multi-tool workflows in real-world settings. However, existing benchmarks typically sepa
arXiv:2608.26153v1 Announce Type: new Abstract: Clinical electroencephalography (EEG) reporting remains largely manual and time-consuming, and current EEG software ecosystems do not produce the struct
arXiv:2608.26118v1 Announce Type: new Abstract: Existing long-form factuality evaluation relies on the decompose-retrieve-verify pipeline. However, the pipeline suffers from noise from claim decomposi
arXiv:2608.27072v1 Announce Type: cross Abstract: A core question in decision-making for agents is whether the relative priorities of competing lower-level objectives can be determined by emotional pr
arXiv:2608.26131v1 Announce Type: new Abstract: As Large Language Models (LLMs) are increasingly deployed to serve open-ended, multi-turn interactions, evaluating conversational quality at human scale
arXiv:2608.26430v1 Announce Type: new Abstract: Parameter-Efficient Fine-Tuning (PEFT) strategies such as Low-Rank Adaptation (LoRA) are effective solutions for fine-tuning large-scale pre-trained mod
arXiv:2608.26129v1 Announce Type: cross Abstract: Scientific peer review datasets have trained AI systems exclusively on Computer Science and Machine Learning venues, producing models that critique ab
As in actual physical heat. How are people coping with the heat that running a decent inference rig pumps out? I've got dual 5060 Ti GPUs and a relatively modest CPU (Intel 14 Core Ultra 5 245KF Deskt
arXiv:2608.26327v1 Announce Type: cross Abstract: Large language models increasingly produce and interpret verbal probability expressions, yet whether these expressions carry consistent meaning across
arXiv:2608.27397v1 Announce Type: cross Abstract: Clinical language models can achieve strong in-hospital accuracy yet fail under deployment shifts because they exploit note-specific artifacts (e.g.,
arXiv:2510.18383v4 Announce Type: replace-cross Abstract: Distilling the tool-use capabilities of large language models (LLMs) into small language models (SLMs) is essential for their practical applic
arXiv:2608.26149v1 Announce Type: new Abstract: Multi-table learning remains a major challenge in machine learning for healthcare and other complex information systems. Relational data combine several
arXiv:2608.26317v1 Announce Type: cross Abstract: Frontier language models are increasingly marketed as omni systems that can perceive and respond across modalities. Existing evaluation frameworks, ho
arXiv:2602.04731v2 Announce Type: replace Abstract: Adapting general-purpose LLMs into domain-specialized dense retrievers typically requires large-scale training on mixed-domain data. We show that me
arXiv:2608.26161v1 Announce Type: cross Abstract: Although Large Language Models (LLMs) demonstrate remarkable capabilities in reasoning and decision-making, high-fidelity probabilistic sampling remai
arXiv:2608.27206v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) demonstrate exceptional visual reasoning capabilities, yet their inference costs escalate rapidly with the proliferation
arXiv:2608.27343v1 Announce Type: new Abstract: This paper addresses the recovery of essay-scale republication and reuse from fragmented text-reuse evidence, a setting whose central challenge is pair-
arXiv:2608.26538v1 Announce Type: new Abstract: High-throughput drug screening relies on low-cost primary assays to prioritize compounds for more expensive dose-response profiling, where potency is ul
arXiv:2608.26324v1 Announce Type: new Abstract: Best-of-N (BoN) sampling is the simplest and most widely deployed inference-time alignment strategy, but it suffers from two distinct problems: reward h
arXiv:2608.26221v1 Announce Type: cross Abstract: As generative AI gains traction, researchers are investigating its potential to serve as proxies for humans. From undergoing cognitive psychology expe
arXiv:2608.27302v1 Announce Type: new Abstract: Accurate identification of the correct view or angle in cardiac ultrasound (echocardiogram) is a critical component of cardiologic imaging. This step is
arXiv:2608.26136v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) decompose language-model activations into sparse, interpretable features, and an appealing way to aim them at reasoning is to
arXiv:2608.26263v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly act as autonomous agents executing complex, long-running procedural skills. Existing agent runtimes maintain e
Learn how Salesforce used Amazon SageMaker AI Inference Component placement (the SchedulingConfig parameter) to distribute model copies across multiple Availability Zones, meeting their Multi-AZ high
arXiv:2608.26511v1 Announce Type: new Abstract: Large language models often exhibit sycophancy, revising their answers to align with users when users push back. Such answer flips, however, can arise f
arXiv:2608.26134v1 Announce Type: new Abstract: Energy forecasting aims to maximize accuracy to ensure energy efficiency by reducing energy waste, an objective that applies equally to on-device foreca
arXiv:2608.26417v1 Announce Type: cross Abstract: Metasurface design increasingly requires fast models that can operate across structurally distinct device families, rather than retraining a separate
arXiv:2608.26706v1 Announce Type: new Abstract: Expert-level financial question answering requires both grounded verification to catch numeric hallucinations and audit trails for regulatory compliance
arXiv:2608.27127v1 Announce Type: new Abstract: Internet memes are a pervasive form of multimodal online communication; however, such communication often involves users from diverse linguistic and cul
arXiv:2608.26638v1 Announce Type: new Abstract: Across various non-verifiable tasks, human evaluation is reliable but expensive, while automatic metrics are more scalable but often biased. Building on
arXiv:2607.09156v2 Announce Type: replace Abstract: Additive activation steering is calibrated in single-turn chat and then deployed inside agent scaffolds. The quantity usually reported for that move
arXiv:2507.18538v3 Announce Type: replace-cross Abstract: Artificial intelligence (AI) and machine learning (ML) are rapidly becoming integral to the 5G Radio Access Network (RAN), enabling beam manag