CoT-Guard: Small Models for Strong Monitoring
arXiv:2605.12746v1 Announce Type: cross Abstract: Monitoring the chain-of-thought (CoT) of reasoning models is a promising approach for detecting covert misbehavior (i.e., hidden objectives) in code g
Knowledge catalogue
arXiv:2605.12746v1 Announce Type: cross Abstract: Monitoring the chain-of-thought (CoT) of reasoning models is a promising approach for detecting covert misbehavior (i.e., hidden objectives) in code g
arXiv:2601.00417v3 Announce Type: replace-cross Abstract: Transformer residual streams evolve by additive accumulation: each layer appends a feature update to a shared hidden state, but has no direct
arXiv:2502.20427v3 Announce Type: replace-cross Abstract: Deepfakes - manipulated or forged audio and video media - pose significant security risks to individuals, organizations, and society at large.
arXiv:2605.13769v1 Announce Type: cross Abstract: We study dense and mixture-of-experts (MoE) transformers in a tiny-scale pretraining regime under a shared LLaMA-style decoder training recipe. The sp
arXiv:2605.13282v1 Announce Type: new Abstract: Classical planners can effectively solve very large deterministic MDPs represented in STRIPS or PDDL where states are sets of atoms over objects and rel
arXiv:2602.06713v2 Announce Type: replace-cross Abstract: Missing data imputation, where a model is trained on observed data to estimate unobserved values, is a fundamental problem in machine learning
arXiv:2605.13332v1 Announce Type: new Abstract: Argumentation is an important topic of AI for modelling and reasoning about arguments. In abstract argumentation, we consider directed graphs, so-called
arXiv:2605.12673v1 Announce Type: new Abstract: Agent benchmarks have become the de facto measure of frontier AI competence, guiding model selection, investment, and deployment. However, reward hackin
arXiv:2605.13349v1 Announce Type: new Abstract: Diffusion-based point editing methods have gained significant traction in image editing tasks due to their ability to manipulate image semantics and fin
arXiv:2605.12998v1 Announce Type: new Abstract: Continual graph learning (CGL) aims to learn from dynamically evolving graphs while mitigating catastrophic forgetting. Existing CGL approaches typicall
arXiv:2605.13156v1 Announce Type: new Abstract: Vision-language models (VLMs) have demonstrated remarkable capabilities in bridging visual perception and natural language understanding, enabling a wid
arXiv:2605.12897v1 Announce Type: new Abstract: DynoJEPP is a factor-graph-based framework that jointly formulates and simultaneously optimizes estimation, prediction, and planning in dynamic environm
arXiv:2605.12887v1 Announce Type: cross Abstract: Web-enabled LLM agents are changing how online information influences search outcomes. Existing Generative Engine Optimization (GEO) studies mainly fo
arXiv:2505.17469v2 Announce Type: replace-cross Abstract: Compression and generalization are fundamentally related through Solomonoff induction and the minimum description length principle (MDL), whic
arXiv:2602.05242v1 Announce Type: cross Abstract: Agentic Test-Time Scaling (TTS) has delivered state-of-the-art (SOTA) performance on complex software engineering tasks such as code generation and bu
arXiv:2605.12920v1 Announce Type: cross Abstract: Effective collaboration between embodied agents requires more than acting in a shared environment; it demands communication grounded in each agent's e
arXiv:2605.13315v1 Announce Type: cross Abstract: Biological neural networks (BNNs) have been established as a powerful and adaptive substrate that offer the potential for incredibly energy and data e
arXiv:2605.12798v1 Announce Type: cross Abstract: Fine-tuning LLMs on narrow harmful datasets can induce Emergent Misalignment (EM), where models exhibit misaligned behavior far beyond the fine-tuning
arXiv:2508.09320v3 Announce Type: replace-cross Abstract: Graph neural networks (GNNs) are increasingly often employed in high-stakes applications, such as fraud detection or healthcare, but are susce
SWE-ZERO and AgentTrove are trending datasets on Hugging Face related to software engineering and agentic AI systems. The post indicates growing interest in trace datasets that capture agent behaviors
arXiv:2605.13402v1 Announce Type: new Abstract: Computing a minimum s-t cut in a graph is a solution to a wide range of computer vision problems, and is often done using the Boykov-Kolmogorov (BK) alg
arXiv:2603.26839v2 Announce Type: replace-cross Abstract: How do multimodal models solve visual spatial tasks -- through genuine planning, or through brute-force search in token space? We introduce ex
Great move. If you’re building agents, so much time is spent engineering your way through traces. And then comes the hard to rapidly iterate and figure out the changes needed. 🚀Launching: LangSmith En
arXiv:2605.13375v1 Announce Type: cross Abstract: In Vision-Language Models (VLMs), processing a massive number of visual tokens incurs prohibitive computational overhead. While recent training-aware
arXiv:2605.12823v1 Announce Type: new Abstract: Coarse-grained (CG) molecular dynamics enables simulations of atomic systems such as biomolecules at timescales inaccessible to all-atom (AA) methods, b
arXiv:2605.13213v1 Announce Type: new Abstract: Multi-modal multi-agent systems (MM-MAS) have gained increasing attention for their capacity to enable complex reasoning and coordination across diverse
arXiv:2605.13536v1 Announce Type: cross Abstract: High-Level Synthesis (HLS) compiles algorithmic C/C++ descriptions into hardware, with Quality of Results (QoR) -- latency and resource utilization --
arXiv:2605.13311v1 Announce Type: new Abstract: Current AI-assisted innovation systems typically apply a single ideation methodology (such as TRIZ or Design Thinking) using sequential prompt-based wor
arXiv:2605.12693v1 Announce Type: new Abstract: Decision-focused learning trains predictive models end-to-end against downstream decision loss, but online settings suffer delayed feedback: outcomes ma
arXiv:2601.21892v2 Announce Type: replace-cross Abstract: Classifier-free guidance (CFG) is a widely used technique for controllable generation in diffusion and flow-based models. Despite its empirica
arXiv:2605.12573v1 Announce Type: cross Abstract: Diffusion-based posterior sampling (PS) is a leading framework for imaging inverse problems, combining learned priors with measurement constraints. Ye
arXiv:2605.13539v1 Announce Type: new Abstract: Simulative and scenario-based testing are crucial methods in the safety assurance for automated driving systems. To ensure that simulation results are r
arXiv:2605.12725v1 Announce Type: new Abstract: Recent video anomaly detection research has expanded rapidly with an emphasis on general models of normality intended to work across many different scen
arXiv:2605.12768v1 Announce Type: cross Abstract: Open time-series forecasting (TSF) benchmarks cover retail, energy, weather, and traffic, but supply-chain logistics remains underserved. We introduce
arXiv:2605.13245v1 Announce Type: new Abstract: Language models can produce convincing scientific analyses, but repeated generations on the same data do not guarantee the same result. A researcher may
arXiv:2603.02175v4 Announce Type: replace-cross Abstract: Instruction-based video editing has witnessed rapid progress, yet current methods often struggle with precise visual control, as natural langu
arXiv:2605.13734v1 Announce Type: cross Abstract: LLMs are widely adopted in production, pushing inference systems to their limits. Disaggregated LLM serving (e.g., PD separation and KV state disaggre
LangSmith Engine is a phase shift because traces are no longer just records to be manually inspected, they’re now the catalyst for recursive agent self-improvement Engine looks at your traces, finds w
arXiv:2605.13137v1 Announce Type: cross Abstract: Proving theorems in Lean 4 often requires identifying a scattered set of library lemmas whose joint use enables a concise proof -- a task we call glob
arXiv:2605.13284v1 Announce Type: cross Abstract: Recent advancements in large language models demonstrate that injecting perturbations can substantially enhance extrapolation performance. However, cu
arXiv:2605.12682v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as reasoning modules in many applications. While they are efficient in certain tasks, LLMs often stru
arXiv:2605.12741v1 Announce Type: new Abstract: Enabling Large Language Models (LLMs) to continuously improve from environmental interactions is a central challenge in post-training. While on-policy s
arXiv:2605.13741v1 Announce Type: cross Abstract: Scene graphs are becoming a standard representation for robot navigation, providing hierarchical geometric and semantic scene understanding. However,
arXiv:2605.12789v1 Announce Type: new Abstract: Large language-vision models (LVLMs) such as CLIP, Flamingo, and BLIP have revolutionized AI by enabling understanding across textual and visual modalit
arXiv:2605.13265v1 Announce Type: new Abstract: Split learning (SL) enables collaborative training by partitioning a neural network across clients and a central server, but the cut-layer interface int
arXiv:2603.02245v3 Announce Type: replace-cross Abstract: Decoding infant cry causes remains challenging for healthcare monitoring due to short nonstationary signals, limited annotations, and strong d
arXiv:2605.13538v1 Announce Type: cross Abstract: Personally Identifiable Information (PII) redaction usually replaces detected entities with placeholder tokens such as [PERSON], destroying the downst
arXiv:2605.12752v1 Announce Type: new Abstract: LoRA is widely adopted for continual fine-tuning of Large Language Models due to its parameter efficiency, modularity across tasks, and compatibility wi
arXiv:2605.12556v1 Announce Type: new Abstract: Low-light image enhancement is challenging due to complex degradations, including amplified noise, artifacts, and color distortion. While Retinex-based
arXiv:2605.13218v1 Announce Type: new Abstract: Cancer is one of the leading causes of death worldwide, making the development of rapid, minimally invasive, label-free and scalable diagnostic strategi
arXiv:2605.13754v1 Announce Type: new Abstract: In this paper, we study the problem of manipulation skill acquisition for performing construction activities consisting of repetitive tasks (e.g., build
arXiv:2605.12824v1 Announce Type: cross Abstract: Large language models (LLMs) can generate high-level diverse phenomena without explicitly programmed rules. This capability has led to their adoption
arXiv:2605.13753v1 Announce Type: cross Abstract: We propose min Generalized Sliced Gromov--Wasserstein (min-GSGW), a sliced formulation for the Gromov--Wasserstein (GW) problem using expressive gener
arXiv:2601.21975v2 Announce Type: replace Abstract: Recent work identifies a stated-revealed (SvR) preference gap in language models (LMs): a mismatch between the values models endorse and the choices
arXiv:2605.13779v1 Announce Type: cross Abstract: We present MindLab Toolkit (MinT), a managed infrastructure system for Low-Rank Adaptation (LoRA) post-training and online serving. MinT targets a set
arXiv:2605.13527v1 Announce Type: new Abstract: Reusable skills have become a core substrate for improving agent capabilities, yet most existing skill packages encode reusable behavior primarily as te
arXiv:2605.12856v1 Announce Type: new Abstract: The emergence of multi-agent systems introduces novel moderation challenges that extend beyond content filtering. Agents with {em malicious intent} may
arXiv:2605.13305v1 Announce Type: new Abstract: Neural ordinary differential equations (Neural ODEs) often fit training trajectories while generalizing poorly to unseen initial conditions and long hor
arXiv:2605.13641v1 Announce Type: new Abstract: Complex reinforcement learning environments frequently employ multi-task and mixed-reward formulations. In these settings, heterogeneous reward distribu
arXiv:2605.13623v1 Announce Type: new Abstract: Diagnosing esophageal motility disorders pose significant challenges due to the complexity of high-resolution impedance manometry (HRIM) data and variab