Knowledge catalogue
I've been tinkering with GLM-5.3-Flash on two 64GB CMP 170HX cards for a while, and the setup is finally stable enough that I figured I'd share it. I also compared it against the Qwen3.8-Flash-Next se
arXiv:2607.10826v2 Announce Type: replace-cross Abstract: Automated evaluation is essential for scaling generative 3D systems, where exhaustive human review is costly and slow. Yet the reliability of
arXiv:2610.07339v1 Announce Type: cross Abstract: Tactical Combat Casualty Care (TC3) requires responders to connect visual observations of injuries and interventions with established clinical guidanc
arXiv:2610.08368v1 Announce Type: cross Abstract: Developing long-acting injectable formulations requires the simultaneous optimization of drug loading, release kinetics, viscosity, injectability, sta
arXiv:2610.08703v1 Announce Type: new Abstract: In K-12 mathematics tutoring, student-tutor dialogue provides rich evidence of learners' problem-solving processes and sources of difficulty. Learning a
arXiv:2610.07694v1 Announce Type: new Abstract: The integrative analysis of histopathological Whole-Slide Images (WSIs) and transcriptomic profiles holds significant promise for cancer survival predic
arXiv:2610.07780v1 Announce Type: new Abstract: Speculative decoding reduces large language model inference latency by drafting multiple tokens before target-model verification, but its effectiveness
arXiv:2610.08417v1 Announce Type: new Abstract: Recent advances in LipSync generation technology have led to the creation of highly realistic videos, posing severe societal risks. However, existing de
arXiv:2606.21399v2 Announce Type: replace Abstract: Runtime oversight often intervenes when an LLM agent's calibrated failure score crosses a threshold. Yet states with the same failure risk can diffe
arXiv:2610.08106v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) advance rapidly, while conventional benchmark development lags behind, delaying investigation of newly observed
arXiv:2610.07502v1 Announce Type: new Abstract: Provider queries are clarifying requests sent by clinical documentation specialists to physicians to close gaps in the clinical note and ensure accurate
arXiv:2610.07907v1 Announce Type: new Abstract: Recurrent neural networks typically compress information into a single vector-valued recurrent state, forcing short-term computation and long-term reten
arXiv:2610.06993v1 Announce Type: cross Abstract: Evolution Strategies (ES) enable memory efficient full parameter fine-tuning of large language models (LLMs) using only forward computation. However,
arXiv:2610.08780v1 Announce Type: cross Abstract: World models offer a data-driven alternative to traditional simulators for robotics, with applications spanning policy evaluation, improvement, and pl
arXiv:2610.08341v1 Announce Type: new Abstract: Recent training-free pruning approaches for Multimodal Large Language Models (MLLMs) effectively cut computational overhead by exploiting visual redunda
arXiv:2610.07659v1 Announce Type: new Abstract: Speculative decoding accelerates autoregressive generation in large language models. In each drafting stage, a lightweight draft model proposes tokens t
arXiv:2610.08102v1 Announce Type: new Abstract: Conversational MLLM agents are increasingly expected to assist in professional workflows, from AI research and engineering design to product management
arXiv:2603.04364v2 Announce Type: replace-cross Abstract: Multimodal web agents that process both screenshots and accessibility trees are increasingly deployed to interact with web interfaces, yet the
arXiv:2610.07848v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning (PEFT) has become a standard approach for adapting large language models to downstream tasks. However, most existing P
Grace Kay / The Information: Elon Musk says Grok Bot will use the “best back end model for any given task, including Claude Opus 5.5, MidJourney, Suno” — Elon Musk announced on Tuesday night that Spac
arXiv:2610.08108v1 Announce Type: new Abstract: Diffusion language models (dLLMs) have emerged as a promising alternative to autoregressive (AR) language models, offering flexible token-update orders
arXiv:2610.06986v1 Announce Type: new Abstract: AI research agents are increasingly used to search over programs, mathematical constructions, and proofs. However, existing systems typically optimize e
arXiv:2610.07676v1 Announce Type: cross Abstract: Research on transformer expressivity shows whether a transformer is capable of solving a given task, but gives little indication of whether the soluti
arXiv:2610.07832v1 Announce Type: cross Abstract: Large language models (LLMs) equipped with terminal access have demonstrated strong capabilities in automating software engineering tasks. However, ex
arXiv:2610.07940v1 Announce Type: cross Abstract: Looped language models apply the same stack of layers T times to each token, which deepens the model without adding parameters but multiplies its key-
As previously promised, here's Anthropic's new fast, low cost model: Introducing Claude Haiku 5.5. The previous Haiku, 4.5, was very much showing its age. It came out almost a year ago, and was priced
arXiv:2610.07663v1 Announce Type: cross Abstract: User behavior simulation is the computational modeling of user interactions within information systems through the use of simulated agents in place of
arXiv:2610.08303v1 Announce Type: new Abstract: Current evaluation of multilingual Large Language Models (LLMs) rests on an implicit Translation-Isomorphism Assumption (TIA): that semantic structures
arXiv:2610.07587v1 Announce Type: new Abstract: LLM orchestration investigates how an orchestrator coordinates a group of autonomous agents to achieve common goals or maximize collective welfare. The
arXiv:2610.08215v1 Announce Type: new Abstract: Learning from experience is essential for LLM agents to adapt to unfamiliar and dynmaic environments. Evaluating this ability is therefore important for
arXiv:2610.08405v1 Announce Type: cross Abstract: Large Language Models have emerged as promising tools for software vulnerability analysis, but their effectiveness depends heavily on prompt design. E
arXiv:2610.07731v1 Announce Type: cross Abstract: Dense retrieval models are typically trained with contrastive objectives that learn effective representations but do not directly optimize retrieval m
arXiv:2610.07937v1 Announce Type: new Abstract: Redpine Science gives models and agents a single access point to a wide range of peer-reviewed literature, queried directly through the Model Context Pr
arXiv:2610.07580v1 Announce Type: new Abstract: Aerospace electrical-design revisions can contain multiple genuine changes, although an engineering request may authorize only a subset. Propagating eve
arXiv:2610.06996v1 Announce Type: cross Abstract: Block diffusion language models keep a large key-value (KV) cache throughout generation and attend to it at every denoising step, limiting both memory
arXiv:2610.08214v1 Announce Type: new Abstract: We report on an approach to teaching logic to mixed groups of computer science, mathematics, and philosophy students, based on the logico-pluralistic Lo
arXiv:2610.07226v1 Announce Type: cross Abstract: ``What are the irreducible conditions that are sufficient to produce an outcome?'' is one of the most common questions that recur across computation a
arXiv:2610.08095v1 Announce Type: new Abstract: Natural-language access to RDF knowledge graphs is a core Semantic Web ambition. Large language models (LLMs) have advanced Text-to-SPARQL, yet on unfam
arXiv:2610.07822v1 Announce Type: new Abstract: Speculative decoding accelerates autoregressive generation by using a lightweight draft model to propose multiple tokens that are verified by a target m
arXiv:2610.07874v1 Announce Type: new Abstract: On-policy distillation (OPD) has been widely studied as a post-training method in which a student model obtains token-level supervision from a stronger
arXiv:2610.07649v1 Announce Type: new Abstract: Large language model (LLM)-based robot task planning is promising for open-ended instruction following, but degrades on long-horizon tasks in large envi
arXiv:2610.07588v1 Announce Type: new Abstract: Modern recommendation is shifting from platform-centric personalization toward user-governed personalization, where a personal LLM agent can act on the
arXiv:2610.08670v1 Announce Type: cross Abstract: Language models increasingly act as agents. An agent that says an action is wrong and then takes it anyway is a different failure from one that does n
arXiv:2610.06999v1 Announce Type: new Abstract: Rapid adaptation to a new environment requires a robot to acquire useful knowledge about local objects, states, and interactions from limited experience
arXiv:2610.07936v1 Announce Type: new Abstract: Systematicity, the probabilistic mapping of form to meaning, permeates language at all levels, and sublexical cues have been shown to govern human pseud
arXiv:2602.11958v2 Announce Type: replace-cross Abstract: Linear attention offers an efficient alternative to full attention with a fixed-size recurrent state. However, this state is shared by all tok
arXiv:2605.06183v2 Announce Type: replace Abstract: Low-rank adaptation (LoRA) is a widely used parameter-efficient fine-tuning method that places trainable low-rank adapters into frozen pre-trained m
arXiv:2610.08448v1 Announce Type: cross Abstract: On-Policy Distillation (OPD) trains a student on its own generations using teacher feedback. With different tokenizers, comparing teacher and student
arXiv:2610.07532v1 Announce Type: cross Abstract: LLMs have advanced rapidly, raising growing concerns about their safety. Recent work has proposed approaches to detect and defend against attacks incl
arXiv:2610.07730v1 Announce Type: cross Abstract: Typed decision models answer a declared question without generating text: a decision head returns a probability for each of the declared options in a
arXiv:2610.08077v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) turns agent experience into learning signals primarily through scalar outcome rewards after intera
arXiv:2602.16863v3 Announce Type: replace-cross Abstract: The ability to manipulate tools significantly expands the set of tasks a robot can perform. Yet, tool manipulation represents a challenging cl
arXiv:2610.07093v1 Announce Type: new Abstract: The rapid proliferation of heterogeneous data sources within the Internet of Things (IoT) across domains such as smart cities, energy management, and en
arXiv:2610.07091v1 Announce Type: new Abstract: The evolution of machine learning has progressively changed where intelligence resides in an AI system. In conventional machine learning the task, data
arXiv:2610.07121v1 Announce Type: new Abstract: Diffusion large language models dLLMs) have emerged as a promising alternative to autoregressive language models through bidirectional diffusion-based t
arXiv:2610.08076v1 Announce Type: new Abstract: Frontier LLM agents have been shown to be capable of solving increasingly complex tasks for which humans have measurable solutions. This begs the pertin
arXiv:2610.07332v1 Announce Type: cross Abstract: Long-horizon LLM agents are frequently implemented using sparse mixture-of-experts (MoE) models, yet the co-design of agentic behavior and MoE structu
arXiv:2610.07004v1 Announce Type: new Abstract: Task planning for LLM agents requires workflows that satisfy both user intent and complex sub-task dependencies. While existing planners work well for s
arXiv:2610.07767v1 Announce Type: cross Abstract: Reinforcement learning (RL) for post-training large language models (LLMs) incurs substantial computation and memory overhead during rollout generatio
arXiv:2610.06962v1 Announce Type: cross Abstract: In many review workflows the verdict is the only thing retained. The passages behind it are not marked, because that annotation costs far more than re