Knowledge catalogue
.@MiniMax_AI M3 model is available on Ollama's Cloud! In partnership with MiniMax, the M3 model on Ollama's Cloud is US-based with zero data retention. Try M3 on coding and agentic tasks: Claude Code:
arXiv:2605.30889v1 Announce Type: cross Abstract: Constructing production-quality machine-learned interatomic potentials (MLIPs) requires balancing accuracy, dynamical stability, and computational thr
arXiv:2605.31387v1 Announce Type: new Abstract: Robots operating in diverse environments rely on visual input to interpret objects and spatial layouts. In human-collaborative tasks, they are expected
arXiv:2511.04393v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed as 'agents' for decision-making (DM) in interactive and dynamic environments. Yet, since they
arXiv:2605.31328v1 Announce Type: new Abstract: Emergent misalignment (EM) is the surprising tendency of language models to become broadly misaligned after fine-tuning on narrowly misaligned examples.
arXiv:2510.14150v5 Announce Type: replace Abstract: We introduce CodeEvolve, an open-source framework that couples large language models with island-based evolutionary search for end-to-end algorithmi
arXiv:2605.29637v1 Announce Type: new Abstract: Large language models recall knowledge reliably in English but often fail on the same query posed in a lower-resourced language -- a crosslingual consis
arXiv:2605.29107v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly rank products, documents, and recommendations for user queries, which makes manipulating these rankings a gr
arXiv:2605.29223v1 Announce Type: new Abstract: The parameter counts of the most widely used large language models (LLMs) are often withheld by their developers, leaving model size -- a primary refere
arXiv:2510.24606v2 Announce Type: replace Abstract: The quadratic cost of attention limits the scalability of long-context LLMs, especially under limited hardware memory budgets. While attention is of
arXiv:2605.29360v1 Announce Type: new Abstract: Action-conditioned world models are increasingly used as scalable simulators for robot learning, yet current evaluations provide limited evidence that t
Most people training agentic LLMs with RL right now have a silently broken training loop and have no idea. Here's the trap: single-turn RL works beautifully. Clean curves, sane rewards, everything con
arXiv:2605.29676v1 Announce Type: new Abstract: Large language models in Agentic AI systems consume tool schemas and execution results and emit tool invocations as structured data. The default languag
arXiv:2605.29659v1 Announce Type: cross Abstract: Real-time safety filtering for large language model (LLM) applications requires classifiers that can detect unsafe prompts, toxic language, jailbreak
arXiv:2605.30052v1 Announce Type: cross Abstract: One-shot Program-of-Thought (PoT) emits a Python program that prints a primitive-action plan; a single invalid action silently invalidates the traject
arXiv:2605.29468v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to support scientific work, but it is unclear whether they uphold responsible conduct of research (
arXiv:2605.29188v1 Announce Type: new Abstract: Dictionary methods, topic models, and embedding-similarity scorers are widely used in CSS and management research to measure constructs such as 'entrepr
arXiv:2601.00065v3 Announce Type: replace-cross Abstract: Tokenizer transplant in cross-vocabulary model composition reconstructs donor-only embedding rows as weighted combinations over shared lexical
arXiv:2605.28313v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in tasks related to reasoning and judgment. However, assessing the quality of arg
arXiv:2605.27485v1 Announce Type: cross Abstract: Formal verification offers a path to provably correct software, but writing verified code remains expensive enough that the technique is rarely used i
arXiv:2605.28183v1 Announce Type: cross Abstract: We introduce the BenGER (Benchmark for German Law) dataset for evaluating LLM systems on subsumption-based legal reasoning in German law. The BenGER d
arXiv:2605.27649v1 Announce Type: new Abstract: Multilingual LLMs are increasingly used when instruction, source content, and required response languages do not coincide. Existing benchmarks have expa
arXiv:2605.27741v1 Announce Type: new Abstract: Audio and omni-modal large language models exhibit impressive cross-modal reasoning capabilities. However, applying standard reinforcement learning post
arXiv:2605.27970v1 Announce Type: new Abstract: While large language models (LLMs) are trained purely on textual data, prior work has shown that their internal representations can exhibit rich geometr
arXiv:2512.20780v3 Announce Type: replace Abstract: Recent work has explored the use of large language models (LLMs) to generate tutoring responses in mathematics, yet it remains unclear how closely t
arXiv:2605.28597v1 Announce Type: cross Abstract: This position paper argues that the AI/ML community should stop overclaiming and retire the label 'positive backdoor,' and instead treat trigger-activ
arXiv:2605.27712v1 Announce Type: new Abstract: Long reasoning traces need reliability estimates before final answers are known. We study prefix-conditioned eventual-success estimation, P(y=1 mid o_{1
arXiv:2605.27750v1 Announce Type: cross Abstract: Recent work has shown that Vision-Language Models (VLMs) used for optical character recognition (OCR) can generate plausible but visually unsupported
arXiv:2605.28003v1 Announce Type: new Abstract: The frontier of mathematics is defined by problems whose solutions are not yet known, yet it remains unclear whether language models can meaningfully en
arXiv:2605.27379v1 Announce Type: new Abstract: We present Soro, a family of Tajik-specialized conversational large language models (LLMs) designed for real-world deployment under tight compute and co
arXiv:2605.28190v1 Announce Type: new Abstract: Embedding benchmarks like MTEB report a single score per model, implicitly treating robustness as a static, scalar property. We argue that embedding rob
arXiv:2605.28700v1 Announce Type: new Abstract: The GSM-Symbolic benchmark (Mirzadeh et al., 2025) reported consistent performance drops across 25 Large Language Models (LLMs) when tested on template-
Today, we're releasing LFM2.5-8B-A1B, a device-optimized model designed to power real-life applications on phones, laptops, PCs, robots, and fast & lightweight server-side use-cases. > 8B MoE, 1.5B ac
arXiv:2605.26130v1 Announce Type: new Abstract: Operational weather prediction at kilometer scales remains computationally prohibitive for traditional numerical weather prediction (NWP) models, limiti
arXiv:2510.13217v2 Announce Type: replace-cross Abstract: Search systems are increasingly used for reasoning-intensive queries, where what makes a document relevant requires understanding or reasoning
arXiv:2605.27268v1 Announce Type: cross Abstract: Modern Large Language Models (LLMs) are often criticized for producing repetitive and homogeneous text, despite possessing vast latent vocabularies. W
arXiv:2605.26548v1 Announce Type: cross Abstract: Large language models (LLMs) now support automated software security tasks, including vulnerability discovery and proof-of-concept (PoC) generation. E
arXiv:2605.26849v1 Announce Type: new Abstract: Sampling multiple responses improves language model reasoning, but uniform compute allocation is inefficient: easy questions are over-sampled while hard
arXiv:2605.24573v1 Announce Type: new Abstract: Understanding why a spacecraft maneuvers -- rather than simply that it did -- is an increasingly important problem for space domain awareness as Earth o
arXiv:2605.24164v1 Announce Type: new Abstract: We describe our submission to the CLPsych~2026 Shared Task on capturing and characterizing mental health changes through social media timeline dynamics.
arXiv:2605.24172v1 Announce Type: new Abstract: Secure patient-provider messages contain clinically important communication behaviors that are difficult to characterize manually at scale. The Electron
arXiv:2605.25856v1 Announce Type: cross Abstract: Large Language Model interfaces are increasingly verbose, exposing intermediate reasoning traces alongside final answers. Traces are framed as transpa
arXiv:2510.14925v4 Announce Type: replace Abstract: High-confidence errors in large language models are often treated as fragile failures. We study an alternative: some errors may be false fixed point
arXiv:2605.24844v1 Announce Type: new Abstract: While general-purpose Large Language Models (LLMs) applied to Geology often hallucinate when reasoning about subsurface structures and deep-time evoluti
arXiv:2605.25520v1 Announce Type: new Abstract: Predicting a label correctly does not necessarily require representing the operation that produces it. Transformer representations are known to carry la
arXiv:2605.24981v1 Announce Type: new Abstract: Choosing a Large Language Model (LLM) for a given task requires comparing many strong candidates, yet standard evaluation relies on costly annotations o
arXiv:2512.15922v3 Announce Type: replace Abstract: Despite initial successes and a variety of architectures, retrieval-augmented generation systems still struggle to reliably retrieve and connect the
arXiv:2605.26064v1 Announce Type: cross Abstract: We present Paris 2.0, the first video generation model pre-trained through decentralized computation. Its training recipe builds upon Paris 1.0 (arXiv
arXiv:2502.15835v5 Announce Type: replace-cross Abstract: Pragmatic reasoning helps interlocutors infer intended meaning from ambiguous or underspecified messages by considering shared context and cou
arXiv:2605.24171v1 Announce Type: cross Abstract: Large language models are increasingly used for vulnerability detection, yet their reliability under different prompt formulations remains uncharacter
arXiv:2605.24218v1 Announce Type: new Abstract: Deep research agents extend the role of search engines from retrieving keyword-matched pages to synthesizing knowledge, fundamentally changing how human
arXiv:2605.23940v1 Announce Type: new Abstract: How do multi-turn reasoning systems fail? The expected answer is logical contradiction, in which the system's maintained state becomes unsatisfiable. We
arXiv:2605.24846v1 Announce Type: cross Abstract: Large language models (LLMs) display strong comprehensive abilities, yet the internal mechanisms that support these behaviors remain insufficiently un
An open source model has returned to #1 on the 3D Design leaderboard by Design Arena. Kimi K2.6 has reached the top of the leaderboard for 3D Design, ahead of models 10X more expensive like Opus 4.7 b
arXiv:2602.18788v3 Announce Type: replace Abstract: We introduce BURMESE-SAN, the first holistic benchmark that systematically evaluates large language models (LLMs) for Burmese across three core NLP
arXiv:2605.23238v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as economic agents in marketplaces, auctions, and bidding settings. Anticipating their behavior i
arXiv:2605.23825v1 Announce Type: cross Abstract: It has generally been assumed that geopolitical bias in language models originates from the training data used during the pre-training phase. We teste
arXiv:2605.23168v1 Announce Type: cross Abstract: When practitioners fine-tune LLMs on unvetted datasets, an adversary can exploit the data supply chain through task-level poisoning: inserting a small
arXiv:2605.22487v1 Announce Type: new Abstract: Recent advances in Multilingual Large Language Models (MLLMs) have significantly enhanced cross-lingual conversational capabilities, yet modeling cultur
arXiv:2605.21852v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in general video understanding, their capacity to interpret invo