3,698 items tracked: 33 reported by two or more outlets, the rest by a single source. Most-corroborated first.
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.
arXiv:2610.07863v1 Announce Type: cross Abstract: Long-horizon LLM agents act on an append-only interaction history that is re-sent to the model at every step, so the context and its cost grow with steps until the sessio…
arXiv:2610.07887v1 Announce Type: cross Abstract: Unified multimodal models (UMMs) integrate understanding and generation, yet their generative behavior is rarely governed by what they understand about the task.
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-value (KV) cache by…
arXiv:2610.07946v1 Announce Type: cross Abstract: Visual disruptions can arise while a robot is executing a task, leaving a vision-language-action (VLA) policy to respond without knowing the disruption type or timing.
arXiv:2610.08097v1 Announce Type: cross Abstract: Mathematical problem solving often requires deterministic computational steps that agents delegate to tools and implicitly trust.
arXiv:2610.08155v1 Announce Type: cross Abstract: Large language model (LLM)-based multi-agent systems (MAS) have become a promising paradigm for complex information-seeking and reasoning tasks by enabling collaborative…
arXiv:2610.08208v1 Announce Type: cross Abstract: We introduce STRUCTURALCOST, a self-paced reading dataset of 475 participants and 40,800 observations isolating the processing cost of long-distance subject-verb dependen…
arXiv:2610.08316v1 Announce Type: cross Abstract: Protein Generative Models (PGMs) have revolutionized structural biology by enabling the design of complex 3D protein structures from sequence data.
arXiv:2610.08331v1 Announce Type: cross Abstract: The rapid integration of Vision Language Models (VLMs) into sensitive systems introduces critical safety vulnerabilities that remain unexplored in exist studies.
arXiv:2610.08350v1 Announce Type: cross Abstract: Visual world models enable goal-directed control through decision-time action search, but their deployment efficiency is often limited by conservatively large planning bu…
arXiv:2610.08401v1 Announce Type: cross Abstract: While recent vision-language models (VLMs) have shown outstanding performance across diverse applications, they tend to under-use visual information and over-rely on text…
arXiv:2610.08448v1 Announce Type: cross Abstract: On-Policy Distillation (OPD) trains a student on its own generations using teacher feedback.
arXiv:2610.08482v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) are increasingly being applied to three-dimensional medical imaging, but their application to knee MRI remains limited, particularly…
arXiv:2610.08501v1 Announce Type: cross Abstract: Depression has no diagnostic blood test.
arXiv:2610.08502v1 Announce Type: cross Abstract: Proactive power management systems reduce processor dynamic power through runtime power prediction and power-aware scheduling.
arXiv:2610.08513v1 Announce Type: cross Abstract: LLMs are increasingly deployed as autonomous agents in social environments, making it critical to study their ability to faithfully simulate human interactions.
arXiv:2610.08595v1 Announce Type: cross Abstract: Deep generative models often produce structured outputs composed of interacting components.
arXiv:2610.08622v1 Announce Type: cross Abstract: System administrators of Internet-scale services need to resolve failure incidents to maintain reliability of such services.
arXiv:2610.08668v1 Announce Type: cross Abstract: Behavioral watermarking embeds an owner identifier in an LLM agent's high-level action choices, giving provenance without touching output tokens.
arXiv:2610.08773v1 Announce Type: cross Abstract: Web agents complete user requests by reading and acting on pages that third parties write, so an instruction planted on a page can redirect the agent away from the user's…
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 planning.
arXiv:2410.05479v2 Announce Type: replace Abstract: Uncertainty-aware explanation methods often produce several alternatives for the same prediction.
arXiv:2507.07426v4 Announce Type: replace Abstract: Recent advances in large language models have demonstrated considerable potential in scientific domains such as drug repositioning.
arXiv:2511.20471v3 Announce Type: replace Abstract: Recent advances in Large Language Model (LLM) reasoning have improved conventional problem solving, but creative reasoning remains comparatively underexplored.
arXiv:2511.20510v3 Announce Type: replace Abstract: Molecule generation from extremely limited training data is a key challenge in drug discovery.
arXiv:2601.04884v4 Announce Type: replace Abstract: Executing a multi-agent plan can be challenging when an agent is delayed, because this typically creates conflicts with other agents.
arXiv:2602.11574v5 Announce Type: replace Abstract: Configuring LLM-based agent systems involves choosing workflows, tools, token budgets, and prompts from a large combinatorial design space, and is typically handled tod…
arXiv:2605.27593v2 Announce Type: replace Abstract: Even when a tool is explicitly described as unfair and harmful to others, ostensibly safety-aligned LLM agents still voluntarily engage in secret collusion whenever doi…
arXiv:2606.05647v2 Announce Type: replace Abstract: AI coding agents are increasingly embedded in real-world software development, collaborating with human developers while gaining broader access to codebases and tools.
arXiv:2606.05761v3 Announce Type: replace Abstract: Persistent AI assistants, such as OpenClaw, accumulate large collections of related memories over long-term interactions.
arXiv:2606.21399v2 Announce Type: replace Abstract: Runtime oversight often intervenes when an LLM agent's calibrated failure score crosses a threshold.
arXiv:2607.12397v2 Announce Type: replace Abstract: LLM agents operate in stateful environments, where a single erroneous step can waste limited interaction budget or cause irreversible effects before task failure become…
arXiv:2607.20471v2 Announce Type: replace Abstract: Personalization is classically a two-party problem: a sender chooses what to say, and a receiver with independent objectives decides whether to act.
arXiv:2609.09815v2 Announce Type: replace Abstract: Compound LLM systems often solve a coordination problem by adding a higher-level LLM.
arXiv:2407.07111v2 Announce Type: replace-cross Abstract: The rapid development of diffusion models (DMs) has significantly advanced image and video applications, making "what you want is what you see" a reality.
arXiv:2408.12549v4 Announce Type: replace-cross Abstract: This paper presents a method for modeling optical dynamic range compressors using deep neural networks with Selective State Space models.
arXiv:2503.22764v3 Announce Type: replace-cross Abstract: The large language model (LLM) is typically integrated into the mainstream optimization protocol.
arXiv:2508.10020v2 Announce Type: replace-cross Abstract: Enhancing LLM reasoning in federated settings is nontrivial due to stringent computational, communication, and privacy constraints, especially in healthcare, wher…
arXiv:2508.14748v2 Announce Type: replace-cross Abstract: The increasing variety of molecular data creates a need for generative models that can flexibly incorporate heterogeneous constraints across modalities.
arXiv:2511.00053v2 Announce Type: replace-cross Abstract: The design of learning objectives is central to training time-series forecasting models.
arXiv:2511.20718v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) algorithms such as PPO and GRPO are widely used to train large language models (LLMs) for multi-turn agentic tasks.
arXiv:2512.11147v2 Announce Type: replace-cross Abstract: AI agents are increasingly granted autonomous access to sensitive user data and third-party services, making effective permission management a critical security c…
arXiv:2601.16390v2 Announce Type: replace-cross Abstract: Large language models exhibit strong multilingual capabilities, yet significant performance gaps persist between dominant and non-dominant languages.
arXiv:2602.16863v3 Announce Type: replace-cross Abstract: The ability to manipulate tools significantly expands the set of tasks a robot can perform.
arXiv:2603.04317v2 Announce Type: replace-cross Abstract: A growing literature shows that variables can be linearly decoded from the activations of large language models (LLMs).
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 their dual-stream archi…
arXiv:2603.16017v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly participate in morally sensitive decision-making, yet how they organize ethical frameworks across reasoning steps remain…
arXiv:2603.23184v2 Announce Type: replace-cross Abstract: Despite the success of reinforcement learning from human feedback (RLHF), existing reward modeling methods largely rely on explicit feedback, which is costly to c…
arXiv:2604.09945v3 Announce Type: replace-cross Abstract: The rapid adoption of large vision-language models (LVLMs) in recent years has been accompanied by growing fairness concerns due to their propensity to reinforce…