Knowledge catalogue
arXiv:2610.16288v2 Announce Type: new Abstract: Frontier LLM agents perform complex interactive tasks, but their inference costs motivate transferring their experience to smaller open-source agents. D
arXiv:2610.19561v1 Announce Type: new Abstract: An early mistake in the generated reasoning can constrain all subsequent reasoning. Repeated-generation methods, like MCMC-based approaches, attempt to
arXiv:2610.20174v1 Announce Type: cross Abstract: Reinforcement Learning on Mixed-domain preference data (Mix-RL) has become the mainstream approach for training general-purpose Generative Reward Mode
arXiv:2610.20609v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models are gaining attention in autonomous driving, inheriting commonsense priors from large language models (LLMs) and wid
arXiv:2610.16213v1 Announce Type: cross Abstract: Embedded platforms increasingly host safety-related streaming functions next to less critical ones. Whether a safety architecture pattern, such as a d
arXiv:2610.16838v1 Announce Type: new Abstract: As language-model agents write code, move money and change records on behalf of users, deciding whether an action is authorized has become a central saf
arXiv:2610.19015v1 Announce Type: new Abstract: Real measurements are too limited to train an accurate indoor pathloss predictor that works across a wide range of buildings. Large-scale synthetic pret
arXiv:2608.01822v2 Announce Type: replace Abstract: Training LLM-based search agents requires high-quality search data: tasks that demand genuine multi-hop retrieval and trajectories that use search t
arXiv:2610.15084v1 Announce Type: new Abstract: Visual agents that interleave reasoning with tool invocation have posed a promising direction for multimodal tasks. However, learning effective tool inv
arXiv:2610.15575v1 Announce Type: new Abstract: Diffusion models have been widely used for various generative tasks. However, recent studies have demonstrated that the internal representations learned
arXiv:2603.23305v2 Announce Type: replace-cross Abstract: We investigate the problem of matching networks where both edge weights and node features are correlated following a specific node corresponde
arXiv:2610.19781v1 Announce Type: cross Abstract: We introduce SNACK, a string representation for probabilistic graph generation that enables sequence models to generate and model graphs with discrete
arXiv:2610.19992v1 Announce Type: new Abstract: Law students are examined through open-text answers: case solutions, essays and memos that apply the law to a set of facts. Such answers are expensive t
arXiv:2610.17131v2 Announce Type: cross Abstract: Dynamic spatial audio reasoning requires a model to associate changing acoustic observations with the correct source and recover its spatial state at
arXiv:2610.15708v1 Announce Type: new Abstract: Coding agents based on frozen language models can improve their performance by refining the external context they rely on, without updating model weight
arXiv:2610.18438v1 Announce Type: cross Abstract: Molecular fragments provide chemically meaningful units, but existing molecular languages rarely make their locations and connections explicit for edi
arXiv:2610.20137v1 Announce Type: new Abstract: Current video object removal methods suffer from prohibitive latency (minutes per video) and non-causal processing that prevents real-time interaction.
arXiv:2610.16661v1 Announce Type: new Abstract: An LLM agent using tools can fail silently. It stops before the task is done, raises no error, and answers fluently. Two kinds of monitor address this,
arXiv:2610.15107v1 Announce Type: new Abstract: Chain-of-thought prompting enables reasoning in large language models but produces explanations that are difficult to verify, expensive to generate, and
arXiv:2407.12703v5 Announce Type: cross Abstract: Fine-tuning pre-trained language models (PLMs) has recently shown a potential to improve knowledge graph completion (KGC). However, most PLM-based met
arXiv:2610.16636v1 Announce Type: cross Abstract: State space models provide efficient linear-complexity processing for long sequences, but their performance frequently degrades as context length grow
arXiv:2610.20292v1 Announce Type: new Abstract: Reliable medical reasoning requires LLMs to dynamically access external biomedical evidence to improve factual trustworthiness and reasoning accuracy. H
Going to try these out to see if they have the same looping behaviors that other Bonsai models have had. Still requires their fork of llama.cpp (branch prism) so dont expect it to work with vanilla ll
arXiv:2609.34322v2 Announce Type: replace Abstract: Verifying LLM-generated answers under a shared computational budget requires jointly deciding which candidates to inspect and which verification att
arXiv:2610.19557v1 Announce Type: new Abstract: Contrastive learning for time series depends on deciding which pairs of inputs should be treated as similar and dissimilar. Because few augmentations re
arXiv:2610.19551v1 Announce Type: new Abstract: Text-to-image models increasingly generate readable Chinese text that still contains local rendering defects, such as a character with an extra or missi
arXiv:2610.17301v1 Announce Type: new Abstract: Language-model agents sometimes act beyond their authorization and then misreport what they did. On CAPE-Bench, matched agent tasks in which one fact de
arXiv:2610.15938v1 Announce Type: new Abstract: Evaluation of text generated by large language models (LLMs) is increasingly delegated to LLMs acting as judges, yet what such a judge must be shown rem
arXiv:2610.19210v1 Announce Type: new Abstract: Transformers are efficient to pre-train at scale because attention permits parallel computation across sequence positions, but long-context inference re
arXiv:2610.19934v1 Announce Type: new Abstract: Weight pruning can degrade the accuracy of large reasoning models (LRMs), yet it remains unclear whether it damages reasoning itself. We find that much
arXiv:2610.18883v1 Announce Type: new Abstract: Token-selection methods for on-policy distillation (OPD) prioritize student-visited positions using diverse signals, including uncertainty, teacher-stud
arXiv:2610.18924v1 Announce Type: cross Abstract: Interpreting electron paramagnetic resonance (EPR) spectra commonly requires repeated forward simulation and optimization of spin Hamiltonian paramete
arXiv:2608.01008v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) can memorize and disclose sensitive information, motivating machine unlearning to remove designated knowled
arXiv:2610.15029v1 Announce Type: cross Abstract: Automated disease classification from patient-reported symptoms requires balancing the speed of lightweight discriminative models against the contextu
arXiv:2610.16333v1 Announce Type: new Abstract: As AI agents increasingly act through external tools, tool results are no longer simple outputs but execution artifacts that must remain correctly assoc
arXiv:2610.20334v1 Announce Type: cross Abstract: A ReAct-style agent accumulates observations, intermediate results, and failed attempts in a single context. As this context grows, stale and off-path
arXiv:2610.20175v1 Announce Type: new Abstract: Parallel drafters such as DFlash and DSpark reduce proposal latency, but early mismatches limit how much of each block can be accepted. Retaining altern
arXiv:2610.19121v1 Announce Type: cross Abstract: Structured pruning reduces LLM inference costs by removing model components to produce smaller dense models. However, existing methods can cause reaso
arXiv:2610.18704v1 Announce Type: new Abstract: In this paper, we propose an extremely efficient, training-free method to extract token-level reward signals directly from an existing deep reward model
Overview llama.cpp v0.7.0 adds the LiliCorr speculative decoding technique and MTP for GLM5-Next, a new GPU cache for MoE experts kept in host memory (--moe-cache-mib, up to ~2.2x decode speedup when
arXiv:2610.20516v1 Announce Type: new Abstract: On-policy self-distillation provides dense supervision for reasoning models via a privileged self-teacher. However, this supervision reflects local toke
arXiv:2610.14939v1 Announce Type: new Abstract: GRPO-style reinforcement learning has advanced vision-language reasoning, but its sequence-level rewards provide limited credit assignment for individua
arXiv:2610.14709v1 Announce Type: cross Abstract: Large language models are increasingly deployed in applications that act on users' long-term behavior histories, from personal assistants to recommend
arXiv:2605.06068v2 Announce Type: replace Abstract: For years, we have built LLM serving systems like any other critical infrastructure, with a single general-purpose stack hand-tuned over many engine
arXiv:2512.23044v3 Announce Type: replace Abstract: Autonomous agents are shifting information seeking from passive retrieval toward proactive, open-ended research, yet this progress has largely bypas
arXiv:2501.12375v4 Announce Type: replace Abstract: Depth Anything has achieved remarkable success in monocular depth estimation with strong generalization ability. However, it suffers from temporal i
arXiv:2610.19424v1 Announce Type: new Abstract: LLM system capabilities depend not only on model parameters but also on the executable harnesses that organize information acquisition, tool use, reason
arXiv:2610.17959v1 Announce Type: cross Abstract: The design of attention mechanisms in long-context large language models faces an ``impossible triangle'' among KV cache size, training and prefill FL
arXiv:2610.19407v1 Announce Type: new Abstract: Vision-language models must reconcile conflicting text and images. Prior work has characterized the resulting behavior in terms of modality biases--e.g.
arXiv:2610.19411v1 Announce Type: new Abstract: A major challenge in wearable device activity recognition is the heterogeneity across datasets in sensor placement, channel count, sampling rate and sub
We want to support the mathematics community in turning progress in AI into deeper human understanding and new discoveries. To support that goal, we are contributing 5 million to a new Simons Foundati
arXiv:2610.15883v1 Announce Type: cross Abstract: Text wrapped in a trigger can be made behaviorally invisible to a language model: omitted from summaries and quotations, ignored in question answering
arXiv:2610.20186v1 Announce Type: new Abstract: Skills are widely assumed to play a central role in career transitions, motivating their use in career path prediction (CPP) systems. In this work, we c
arXiv:2610.17643v1 Announce Type: new Abstract: An enterprise agent that answers under a written policy must choose an action before it says anything: answer, ask for a missing fact, ask for confirmat
arXiv:2610.15492v1 Announce Type: new Abstract: Skill internalization aims to convert externally specified procedural skills into persistent model capabilities, allowing language-model agents to execu
arXiv:2610.14334v1 Announce Type: new Abstract: In Model Context Protocol (MCP) systems, LLMs select tools from metadata rather than from their implementations. Names and descriptions summarize what a
arXiv:2610.19583v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly used to generate text, their misuse has become a growing societal problem, with implications for acad
arXiv:2610.20107v1 Announce Type: new Abstract: Web agents built on vision language models decide every action by generating text such as click(12), although most of that text encodes a choice among a
https://preview.redd.it/kudj7xii5ivh1.png?width=1508&format=png&auto=webp&s=07712e81310b81aceb2cf8f4d8a7c2eadeb0c304 Just built a new PC, full parts list is here. I am using Deadcode's Radiance infere
arXiv:2610.18108v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as judges to predict which of two candidate answers a human evaluator would prefer, providing a scala