Ask About the Right Moment: Training-Free Object Identity Reasoning for Video-Language Models
Many questions about a video concern one physical object. Where does the ball end up after the cups are shuffled?
nlp
MLINFO COLLECTION
LLM Fine-tuning
LoRA、RLHF、SFT、軽量ファインチューニングなど、LLMを用途に合わせる技術を扱います。
記事一覧
26 / 36From Structured Records to Patient Narratives: Preserving Clinical Alignment in LLM-Generated Health Summaries
As wearable and digital health systems increasingly generate longitudinal physiological records, communicating these observations in patient-accessible language remains a significant challenge. Large…
nlp
Adaptive Skill Granularity for Coding Agents: Runtime Routing and Macro-to-Micro Recovery
Reusable skills allow large language model agents to package task-specific procedures, tool affordances, and execution guidance into modular units. Prior work has largely studied how agents retrieve,…
deep-learning
DIAL: Steerable Language Models with Distilled Instruction-Adherence Levels
When a user says "Keep it short", how short should the LLM's response be? More generally, users and applications require different levels of instruction adherence, but prompting does not reliably…
deep-learning
Drift Says When, Budget Says How Much: Rate-Controlled KV Re-selection for Long-Form Multimodal Generation
KV cache compression for multimodal LLMs usually selects the visual tokens to keep once, at prefill, and reuses that selection for the whole generation. We show that this one-shot selection is…
nlp
PhysTrace: Interpretable Temporal Evaluation of Physical Consistency in Video Generative Models
World action models increasingly rely on pretrained video models assumed to capture physical dynamics for prediction, planning, and action generation. Existing evaluations assess plausibility, probe…
nlp
Predictable performance is suboptimal, and what it means for model routing
Large language models (LLMs) differ in capabilities and costs, motivating routing methods that adaptively choose a model for each query. These methods rely on performance prediction: given a query,…
nlp
Post-Hoc Feature Selection Layer for Neural Networks Interpretability
The interpretability of complex neural networks remains a critical challenge, especially for models already deployed in high-stakes domains. To address this, we adapted the Feature Selection Layer…
deep-learning
SyRA-CS: Synthetic-to-Real Adaptation for Code-Switched ASR with Meta-Learning
Code-switched (CS) automatic speech recognition (ASR) remains difficult because real CS speech is scarce and synthetic speech does not fully match it. We investigate whether synthetic CS speech is…
deep-learning
Major Revision, Minor Accountability: LLMs as Reviewers of Published Articles in Top-Tier Journals
With the growth of scientific output, the peer review system is approaching a breaking point: reviewers are increasingly hard to secure, and turnaround times lengthen accordingly. LLM-assisted or…
deep-learning
AgentPhishing: A Benchmark of LLM Email Agents Under Adaptive Attack
Computer-use agents increasingly handle private information and act on users' behalf across desktop and web applications, including email. Phishing therefore poses privacy and security risks that…
nlp
Parameter-Efficient Adaptation of Large Language Models to a Low-Resource Agglutinative Language: A Corpus, Datasets, and a Reproducible Benchmark for the Bashkir Language
Bashkir is a low-resource agglutinative language written in Cyrillic and remains poorly represented in modern LLMs. We present an open resource suite and a systematic benchmark of adaptation methods:…
deep-learning
Certified Execution Harness for Agentic AI: Safe and Least-Intrusive Petri-Net Supervisory Control Between Reasoning and Action
This paper studies the problem of safe tool execution for large language model (LLM) agents under prompt injection. Using Petri nets, we formalize the execution harness between the LLM and its tools…
nlp
AfterDeleteBench: Auditing Post-Deletion Information Persistence in LLM Agents
Many LLM agents maintain external persistent memory and derive additional state from past interactions, such as summaries. Deleting an original memory record therefore need not remove information…
nlp
Automating Feature Flag Cleanup at Scale with Multi-Agent LLM Systems: An Industrial Experience at DoorDash
Feature flags are runtime configuration mechanisms used for gradual feature rollouts, experimentation, and kill switches. Once a feature is fully rolled out, the flag and its gated code become…
nlp
ValuSpec: Plug-and-Play Candidate Valuation before Target Verification for Tree-Based Speculative Decoding
Tree-based speculative decoding accelerates large language model inference by verifying multiple candidate branches in parallel. However, in practical serving scenarios, similar requests repeatedly…
nlp
Harmful Responses Are Jailbreak Templates: Transferring Autoregressive Jailbreaks to Diffusion Language Models
Diffusion large language models (dLLMs) enable flexible masked generation through bidirectional context modeling, but this capability also introduces a distinct jailbreak attack surface. We find that…
nlp
AgenticEvolve: Evolutionary Program Search with Persistent Language Model Agents that Design and Run Experiments
Evolutionary program search with large language models keeps the structure of an evolutionary algorithm and uses the model as its variation operator. Typically, the model generates each candidate…
nlp
Bridging the Data Gap: Source-Informed Task-Space Transport for Few-Shot Diffusion
Many deployments require a model to move rapidly from a data-rich source to a related target observed only sparsely. This is especially consequential where target data are difficult to collect, as in…
nlp
Data-Driven Vision-Language Models for Remote Sensing: A Survey
During the deep learning era, innovations in remote sensing (RS) vision models primarily focused on optimizing network architectures for specific tasks and conducting end-to-end training. However,…
nlp
PiHand: Latent Hand-Object Interaction Priors for Physics-Based Policy Learning
Synthesizing physically grounded dexterous hand-object interactions is important for VR/AR, gaming, and robotics, yet remains challenging because subtle contact dynamics, diverse object geometries,…
nlp
Beyond Accuracy: Disentangling Decomposition from Typed-State Quality Assurance in Multi-Agent LLM Pipelines
Multi-agent LLM pipelines are often credited with gains in software engineering tasks, but it is rarely clear whether a gain stems from the typed contract between agents or from the specialized…
nlp
CoWriter: Guiding Methodological and Synergetic Human-LLM Co-Authoring
While LLMs have transformed text generation, standard chat-and-canvas interfaces often reduce human authoring to quite passive supervision, causing review fatigue, over-reliance on AI, and the…
nlp
Memory-Aware Reward Modeling: Learning Human Preferences for LLM Memory Use
Memory enables language model assistants to maintain continuity across sessions and generate personalized responses, but knowing more about a user does not necessarily produce responses they prefer.…
nlp