The article reports that on a set of 100 randomly selected tasks from an internal Binary Exploitation benchmark, GLM‑5.3 achieved full control‑flow hijacks in 4% of the trials, while Claude Mythos Preview did so in 6%. Both models outperform earlier versions such as Claude Opus 4.6 and GLM‑5.2, which succeeded in none of the trials. This indicates that a significant threshold in adversarial exploitation capabilities has been crossed by the newer models.
As the chain-of-thought reasoning capabilities of large language models improve, evaluating and calibrating their reasoning confidence is becoming increasingly important for quantifying the uncertaint...
Generative models for function-valued data, such as time series and solutions of partial differential equations, must learn distributions over infinite-dimensional spaces. Functional Flow Matching (FF...
An agent skill is a reusable, actionable natural-language artifact that guides an agent to perform a task effectively under a given harness. Recent studies have explored the optimization of agent skil...
Large language models (LLMs) are increasingly proposed as decision assistants who must reason probabilistically from available evidence under explicit decision costs. We propose a decision-theoretic f...
Embodied systems must make knowledge acquired during one encounter usable in another despite changes in viewpoint, motion, and illumination. Yet aggregate cross-video accuracy conflates failures of lo...
Multimodal continual instruction tuning (MCIT) aims to enable multimodal large language models to acquire new capabilities from sequential tasks while preserving previously learned knowledge. Existing...
Reinforcement Learning with Verifiable Rewards (RLVR) methods such as GRPO rely on successful self-generated trajectories, but finite rollout budgets can produce all-fail groups with no reward-based p...
The article reports on a benchmark that reduced 1,000 Apache Iceberg files to just six, then measured how this consolidation affected query performance across three SQL workloads. It details the methodology and results of the experiment, highlighting changes in execution speed and resource usage. The findings illustrate the trade‑offs between file count and query efficiency in large data systems.
By Thomas Reid
The ByteTrack algorithm is a widely used and computationally efficient multi-object tracking architecture. Its core innovation lies in the combination of lenient bounding box associations with trackle...
Concept Bottleneck Models (CBMs) built on vision-language models such as CLIP represent a latent space as human-understandable concepts. These representations are unfaithful: related concepts are enta...
Photographic evidence is becoming increasingly vulnerable to forms of alteration and fabrication that existing legal and technical workflows are not well equipped to evaluate. Surveillance frames, das...
We introduce Context Language Models (CLMs), language models that natively manage their own context. We implement this by treating the context as a file and allowing the model to make unrestricted upd...
Audio-visual large language models (AVLLMs) have made remarkable progress in multimodal understanding and reasoning through interactions among visual, auditory, and linguistic information. However, re...
While Large Vision-Language Models (LVLMs) achieve remarkable success, hallucinations remain a significant barrier to their reliable deployment. Recent studies primarily attribute these issues to cros...
An agent that uses tools typically responds to what the user explicitly asks, yet completing the task may require information the user never requested. Work on proactive agents mainly studies whether...
Modern coding agents can deliver increasingly large repository-level changes, and recent benchmarks reflect this by emphasizing long-horizon tasks with large reference implementations. Many benchmarks...
Skill evolution improves the capabilities of large language models by analyzing trajectories generated under a given skill and modifying the skill accordingly. Existing approaches typically generate a...
DANCo (Dimensionality from Angle and Norm Concentration) jointly calibrates nearest-neighbor distance and angular statistics and consistently reaches state-of-the-art accuracy on clean intrinsic-dimen...
LLM-based multi-agent systems (MAS) increasingly use latent collaboration to avoid the information loss and repeated encoding-decoding overhead of natural-language communication. However, directly for...