Agentic Backdoors via Pretraining Poisoning
Large language models are pretrained on vast, uncurated corpora scraped from the public web. This creates a security risk from attackers who plant poisoned content in the pretraining data.
nlp
MLINFO COLLECTION
自然言語処理
記事一覧
15 / 44OpenFrontiers: A Collection of Open Research Problems and a Benchmark for Scientific Rediscovery
Large language models (LLMs) have shown increasing promise in research-level problem solving, yet a comprehensive collection of such problems is still missing, and evaluating them on research-level…
nlp
ThinkJev: One Thought, Every Budget for Calibrated Typed Decisions
Many uses of language models end in a typed decision: a choice among a closed set of options, whose probabilities code can act on. Reading those probabilities from one forward pass is fast but often…
nlp
ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning
Vision-Language-Action (VLA) models have made substantial progress in robotic manipulation, but their generalization remains constrained by the diversity and coverage of action-labeled robot…
nlp
Heads of Security: Learned Attention Gates Improve Prompt Injection Robustness
We introduce Heads of Security (HoS), a prompt injection defense that enforces instruction-data separation via a small set of learned per-head attention gates. HoS learns how each head should…
nlp
Pushing Dexterity and Safety for In-Hand Object Pose Reaching That Works Remarkably Well
Dexterous manipulation with multi-fingered hands is the next frontier of robotics, yet learned hand skills remain limited to simple grasps or basic repeated motions, such as rotating an object. As…
nlp
GEPA-Curator: Curated Learning for Self Improving Agents
Large Language Models (LLMs) are increasingly used in multi-turn agentic workloads that require sustained interaction with complex environments. Existing reflective prompt optimizers such as GEPA…
nlp
Can LLMs Uncover Hidden Physical Laws through Free Exploration?
Scientific discovery often begins with an unexpected observation that prompts a new research question. In a world with altered physical laws, can large language models (LLMs) notice unexpected…
nlp
Rare, Relevant, and Still Wrong: How Memory Fails LLM Group Decisions
When an LLM group's discussion is compressed into a short memory for a final decision maker, what should the memory keep? Two natural heuristics keep the rarest claims or the claims relevant to the…
nlp
Agentic Distributional Regression: Conditional Density Estimation through Agent-Written Programs
Artificial intelligence offers statisticians a new paradigm for modelling and analysing complex datasets. Agents based on large language models can reason about data and automate key stages of the…
nlp
Rendering-Free Event Frame Simulation for Fast Reinforcement Learning of Autonomous Robot Navigation
Event cameras offer low latency, high dynamic range, and milliwatt-level power consumption, making them ideal for agile robots such as tiny drones navigating through cluttered environments. However,…
nlp
Leveraging Distributed Sensing and Hyperdimensional Computing for Non-Line-of-Sight Passive Object Sensing
In smart factory environments, passive entities such as humans and movable obstacles may interfere with autonomous robot operations, posing significant safety risks. Detecting potential conflicts…
nlp
World Dreamer v5-lite: A Multi-Robot World Action Model with One Dreamer
Multi-robot control requires integrating distributed camera views while predicting separate action sequences. Most vision-language-action and world-action models target one robot.
nlp
Teach reality, not ethics: a drop-in continued-pretraining corpus installs coupled human-biosphere-AI welfare dispositions across model families
Large language models (LLMs) are increasingly used to make and execute decisions that affect living systems. Yet, to our knowledge, ecological reasoning is not a focus of pre- or post-training.
nlp
What Carries Forward? Pretraining Disclosure Across Language Model Releases
Understanding how language models were pretrained requires information about their data, processing procedures, and computational resources. However, it remains unclear whether successive releases…
nlp
ETAMem: Decoupling and Aligning Heterogeneous Memory for Long-Term Conversational Agents
Long-term memory enables Large Language Models (LLMs) to maintain coherent and personalized interactions across extended conversations. However, existing memory systems face two key challenges: (1)…
nlp
Learning Quality-Controllable Robot Policies with Iterative Hindsight Relabeling
Robot policy evaluation often relies on a binary success signal for task completion. In real-world deployment, however, desired execution behaviors are also defined by quality attributes such as…
nlp
Generalizable Target-Less Joint Intrinsic-Extrinsic Camera-LiDAR Calibration using Deep Pixel-Point Correspondences
Accurate camera-LiDAR calibration is an essential prerequisite for robust multi-modal perception in robotics. Recent target-less methods based on learned pixel-point correspondences achieve high…
nlp
UCVE: Graph Structured Retrieval for Compliance Validation
Structured compliance validation requires determining whether every obligation in a predefined requirement space is satisfied, violated, or unaddressed by a given document. This can be described as a…
nlp
Understanding Human-Robot Collaboration through Joint Action
Human-robot collaboration requires partners to coordinate interdependent contributions toward a shared goal. Joint Action theory provides concepts for understanding this coordination, but how these…
nlp
Where Should the Evaluation Budget Go in LLM-Driven Agent Scaffold Evolution?
Large language model (LLM)-driven agent scaffold evolution improves agent workflows through iterative candidate generation and evaluation. Evaluation both guides subsequent search and determines the…
nlp
Your Policy Is Secretly a Harness: The Decision Geometry of Agent Interfaces
Language model agents are post-trained and deployed through a harness, the prompts, tools, and control logic that present a task to the model and execute its outputs. Harnesses are often revised and…
nlp
Aligning Large Language Models for Safety in African Languages: A Case Study of Hausa
Safety alignment research for large language models (LLMs) remains concentrated on high-resource languages, leaving open how existing alignment methods perform in low-resource, culturally distinct…
nlp
Decision Models as Judges for Hallucination Detection
Large language models are widely used as judges of model outputs (LLM-as-a-Judge), but they are costly and can hallucinate or be overconfident. Decision models are a potential alternative.
nlp