Knowledge catalogue
arXiv:2512.21204v2 Announce Type: replace Abstract: Human infants, with only a few hundred hours of speech exposure, acquire basic units of new languages, highlighting a striking efficiency gap compar
arXiv:2604.17880v1 Announce Type: cross Abstract: Vision-language-action (VLA) models have achieved great success on general robotic tasks, but still face challenges in fine-grained spatiotemporal man
arXiv:2601.04052v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have demonstrated impressive capabilities in generalized robotic control; however, they remain notoriously
arXiv:2604.17358v1 Announce Type: new Abstract: While recent Spoken Language Models (SLMs) have been actively deployed in real-world scenarios, they lack the capability to discern Third-Party Interrup
arXiv:2601.06116v2 Announce Type: replace-cross Abstract: Generative AI models reproduce the biases in the training data and can further amplify them through mode collapse. We refer to the resulting h
arXiv:2604.17551v1 Announce Type: new Abstract: Standard approaches to goal-conditioned reinforcement learning (GCRL) that rely on temporal-difference learning can be unstable and sample-inefficient d
arXiv:2507.14922v2 Announce Type: replace Abstract: Persona-driven simulations are increasingly used in computational social science, yet their validity critically depends on the fidelity of the under
arXiv:2604.18573v1 Announce Type: new Abstract: Despite recent progress, vision-language encoders struggle with two core limitations: (1) weak alignment between language and dense vision features, whi
arXiv:2510.09671v2 Announce Type: replace Abstract: Table Question Answering (TQA) aims to answer natural language questions about tabular data, often accompanied by additional contexts such as text p
arXiv:2604.17698v1 Announce Type: cross Abstract: Reliable deployment of language models requires two capabilities that appear distinct but share a common geometric foundation: predicting whether a mo
arXiv:2604.17114v1 Announce Type: new Abstract: Frontier large language models generate clinically accurate outputs, but their citations are often fabricated. We term this the Provenance Gap. We teste
arXiv:2604.17739v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a prevalent paradigm for training tool calling agents, which typically requires online interactive environments
arXiv:2508.11281v3 Announce Type: replace Abstract: Detecting toxic content using language models is crucial yet challenging. While substantial progress has been made in English, toxicity detection in
arXiv:2602.09130v3 Announce Type: replace Abstract: Model compression is increasingly essential for deploying large language models (LLMs), yet existing comparative studies largely focus on pruning an
arXiv:2407.06048v2 Announce Type: replace Abstract: We present Vision-Braille, the first publicly available end-to-end system for translating Chinese Braille extracted from images into written Chinese
We are entering an extremely exciting era for open-weight models. Kimi K2.6 now feels like a top agentic model. I took it for a spin via @FireworksAI_HQ fast inference APIs. Kimi K2.6 has impressive a
arXiv:2508.16464v2 Announce Type: replace Abstract: Entities in discourse vary in salience: main participants, objects and locations stay prominent, while others are quickly forgotten, raising questio
arXiv:2602.11938v5 Announce Type: replace Abstract: Large language models (LLMs) perform well on well-posed questions, yet standard question-answering (QA) benchmarks remain far from solved. We argue
arXiv:2503.14281v4 Announce Type: replace-cross Abstract: AI coding assistants are widely used for tasks like code generation. These tools now require large and complex contexts, automatically sourced
arXiv:2604.15958v1 Announce Type: cross Abstract: Despite the considerable promise of Retrieval-Augmented Generation (RAG), many real-world use cases may create privacy concerns, where the purported u
arXiv:2604.15789v1 Announce Type: new Abstract: As Large Language Models (LLMs) receive increasing attention and are being deployed across various domains, their potential risks, including generating
arXiv:2604.16239v1 Announce Type: cross Abstract: In multi-fidelity optimization, biased approximations of varying costs of the target function are available. This paper studies the problem of optimiz
arXiv:2604.14309v2 Announce Type: replace-cross Abstract: To address high data traffic demands of sixth-generation (6G) networks, this paper proposes a novel architecture that integrates autonomous ae
arXiv:2604.15857v1 Announce Type: new Abstract: Recent digital media advancements have created increasing demands for sophisticated portrait manipulation techniques, particularly head swapping, where
arXiv:2604.16205v1 Announce Type: cross Abstract: Computational X-ray absorption near-edge structure (XANES) is widely used to probe local coordination environments, oxidation states, and electronic s
arXiv:2604.15647v1 Announce Type: new Abstract: Measuring the quality of public deliberation requires evaluating not only civility or argument structure, but also the informational progress of a conve
Claude Token Counter, now with model comparisons I upgraded my Claude Token Counter tool to add the ability to run the same count against different models in order to compare them. As far as I can tel
arXiv:2604.15663v1 Announce Type: cross Abstract: Code search, framed as information retrieval (IR), underpins modern software engineering and increasingly powers retrieval-augmented generation (RAG),
arXiv:2604.15594v1 Announce Type: cross Abstract: Modern datacenters schedule heterogeneous workloads across geo-distributed sites with diverse compute capacities, electricity prices, and thermal cond
DFlash for Qwen3.6-35B-A3B just dropped ⚡ The community was running the day-1 preview before we even finished training. Now it's done: ✅ Training complete ✅ Validation passed ✅ Weights finalized ↓ Go
arXiv:2604.15839v1 Announce Type: new Abstract: Most ATP benchmarks embed the final answer within the formal statement -- a convention we call 'Easy Mode' -- a design that simplifies the task relative
arXiv:2503.13543v2 Announce Type: replace-cross Abstract: Federated Prototype Learning (FedPL) has emerged as an effective strategy for handling data heterogeneity in Federated Learning (FL). In FedPL
arXiv:2603.03332v3 Announce Type: replace-cross Abstract: Chain-of-Thought (CoT) prompting has emerged as a foundational technique for eliciting reasoning from Large Language Models (LLMs), yet the ro
Free ~20-50% tok/s on a local llama.cpp setup if you already have a draft model sharing vocabulary with your main one. Local stack quietly got faster this weekend https://x.com/TechIno219886/status/20
arXiv:2604.15495v1 Announce Type: new Abstract: Navigating complex, densely packed environments like retail stores, warehouses, and hospitals poses a significant spatial grounding challenge for humans
arXiv:2604.15415v1 Announce Type: cross Abstract: Large language models (LLMs) have evolved into autonomous agents that rely on open skill ecosystems (e.g., ClawHub and Skills.Rest), hosting numerous
how to set up hermes agent step by step. built-in memory, 40+ tools, works on your phone, and what to think of hermes vs openclaw: 1. hermes is a personal AI agent that runs in your terminal. think of
arXiv:2604.15607v1 Announce Type: cross Abstract: AI design characteristics and human personality traits each impact the quality and outcomes of human-AI interactions. However, their relative and join
arXiv:2510.23536v2 Announce Type: replace Abstract: Intent identification serves as the foundation for generating appropriate responses in personalized question answering (PQA). However, existing benc
arXiv:2604.15618v1 Announce Type: new Abstract: We investigate Functional Majority Voting (FMV), a method based on functional consensus for code generation with Large Language Models, which identifies
Moonshot AI today released Kimi-K2.6, the latest addition to its popular Kimi series of open-source large language models. The Chinese artificial intelligence startup says that the algorithm outperfor
Nice paper combining the strength of Skills and RAG. Most RAG systems retrieve on every query, whether the model needs help or not. This is wasteful when the model already knows the answer, and often
arXiv:2604.15830v1 Announce Type: new Abstract: Reinforcement learning has become a powerful approach for enhancing large language model reasoning, but faces a fundamental dilemma: training on easy pr
arXiv:2604.15945v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) is widely used to augment the input to Large Language Models (LLMs) with external information, such as recent or do
arXiv:2511.03056v2 Announce Type: replace-cross Abstract: Conversational AI is constrained in many real-world settings where only one side of a dialogue can be recorded, such as telemedicine, call cen
arXiv:2601.03699v2 Announce Type: replace Abstract: As large language models (LLMs) become integral to safety-critical applications, ensuring their robustness against adversarial prompts is paramount.
arXiv:2603.20633v3 Announce Type: replace Abstract: We present Seed1.8, a foundation model aimed at generalized real-world agency: going beyond single-turn prediction to multi-turn interaction, tool u
arXiv:2509.05489v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards has significantly advanced reasoning in large language models (LLMs), but such signals remain coarse,
arXiv:2604.16022v1 Announce Type: new Abstract: As Large Language Models (LLMs) transition from text processors to autonomous agents, evaluating their social reasoning in embodied multi-agent settings
arXiv:2604.15357v1 Announce Type: cross Abstract: Precise estimation of model inference latency is crucial for time-critical mobile edge applications, enabling devices to calculate latency margins aga
arXiv:2604.15409v1 Announce Type: cross Abstract: KV caching is a ubiquitous optimization in autoregressive transformer inference, long presumed to be numerically equivalent to cache-free computation.
arXiv:2512.07515v4 Announce Type: replace-cross Abstract: Detecting hallucinations in Retrieval-Augmented Generation remains a challenge. Prior approaches attribute hallucinations to a binary conflict
arXiv:2505.24672v2 Announce Type: replace Abstract: Large Language Models (LLMs) excel in various natural language processing tasks but remain vulnerable to generating harmful content or being exploit
arXiv:2510.04237v5 Announce Type: replace Abstract: In this paper, we propose a novel kernel stochastic gradient descent (SGD) algorithm for large-scale supervised learning with general losses. Compar
arXiv:2604.15827v1 Announce Type: cross Abstract: Conventional information retrieval is concerned with identifying the relevance of texts for a given query. Yet, the conventional definition of relevan
arXiv:2512.14554v5 Announce Type: replace-cross Abstract: The rapid advancement of large language models (LLMs) has enabled new possibilities for applying artificial intelligence within the legal doma
arXiv:2509.23175v2 Announce Type: replace-cross Abstract: With the rise of Web 2.0 and microservices, the increasing availability of Web APIs has intensified the need for effective recommendation syst
arXiv:2502.20689v4 Announce Type: replace Abstract: Large Language Models (LLMs) offer promising opportunities to support mental healthcare workflows, yet they often lack the structured clinical reaso
GDPval is one of the most important benchmarks of AI ability because it is based on human expertise. It compares expert human performance to AI performance using expert human judges who spend an avera
b8824 is a llama.cpp release that optimizes HMX matmul operations, including refactoring functions to use size_t for tile counts and improving readability of core matrix multiplication routines. Relea