Instruction

Follow this topic Ask about this topic

Recent momentum

-43%

8 papers in the last 28 days · 0.1% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-21

1 new paper

A weekly snapshot of new work published in Instruction.

Period ending 2026-09-14

4 new papers

A weekly snapshot of new work published in Instruction.

109 papers

Latest in Instruction

Browse all topics →

C $^2$ Nav: Compare Before You Commit for Zero-Shot Vision-and-Language Navigation
Sep 14, 2026Runtian Zheng, Congpeng Zhang, Ying LiuVision-Language Navigation Navigation
ContractEval: Query-Conditioned Execution Matching for Procedural Instruction Conformance
Sep 10, 2026Praphul Singh, Shanu Kumar, Akshat Agarwal +1Kernel Contracts Large Language Model Judges
Stabilizing Instruction Supervision for Instruct-TTS via Controllable Diversification and Drift Filtering
Sep 8, 2026Yizhong Geng, Kecan Mao, Qifei Li +6Instruction Tuning Instruction
In-Place Instruction Following in Diffusion Language Models
Sep 7, 2026Zheng Nie, Zherui Li, Jiaming Zhang +3Diffusion Language Models Instruction-Tuned Models
Instruction Duplication as an Inference-Time Control Primitive
Sep 3, 2026Victor LavrenkoInstruction Instruction-Tuned Models
DuplexSpeechBench-IFEval: Evaluating Implicit Instruction Following in Full-Duplex Voice Agents
Sep 3, 2026Puneet Mathur, Dinesh ManochaFull-Duplex Speech Models Voice Agents
DICS: Exploring Data Intrinsic Consistency for Visual Instruction Selection
Aug 31, 2026Yuyang Hong, Jinhui Guo, Jiaqi Gu +6Vision-Language Alignment Instruction
VIBE: Video Instruction-aligned Background music gEneration
Aug 31, 2026Aryan Vijay Bhosale, Vaibhavi Lokegaonkar, Vishnu Raj +5Music Generation Vibe Coding
Are You Sure You're Sure? On the Impact of Instruction Tuning on Confidence and Lexical Diversity
Aug 13, 2026Irina Proskurina, Mayank Kumar, Oyindolapo O. KomolafeInstruction Tuning Instruction-Tuned Models
Large Language Models Can Follow Instructions, But Not Many at Once: Phase Transitions in Compositional Constraint Satisfaction
Aug 12, 2026Mariya I. VasilevaLarge Language Model Performance Constraint Satisfaction
Do Text-to-Music Models Really Follow Instructions? A Counterfactual Evaluation of Key and Beat Grouping
Aug 12, 2026Yining WangMusic Generation Instruction
Harness-IF: Evaluating Instruction Following Across Instruction Surfaces in Coding Agents
Aug 12, 2026Zining Huang, Haoran Que, Hong Zeng +8Coding Agents Instruction
Agentic Instruction Data Selection: Let DataMaster Interpret Your Intent
Aug 11, 2026Fanqi Zhou, Qiaosheng Chen, Zixian Huang +1Data-Curation Instruction
UNSPECIFIC: General Constraint Synthesis for Breaking Copy-and-Paste Shortcut in LLM Instruction Following
Aug 10, 2026Jeet Sharma, Balpreet Kaur, Jeremiah Hong +2Instruction-Tuned Models Instruction
Goal-oriented Navigation Instruction Generation with Tour Video Priors
Aug 9, 2026Fangdi Li, Juncheng Liao, Changxu Cheng +4Object Goal Navigation Agentic Video Generation
InstructionCrafter: Generating Consistent and High-Fidelity Visual Instructions
Aug 9, 2026Shun Okamoto, Satoshi Iizuka, Kazuhiro FukuiVisual Generation Instruction
When Experience Becomes Instruction: Trajectory Poisoning in Self-Evolving Agent Skill Systems
Aug 6, 2026Jialuo Chen, Lingqi Jiang, Xinhao Deng +7Skill Evolution Poisoning
AIDE: Automated Instruction via Distilled Expertise for Reference-Free Motor Skill Coaching
Aug 4, 2026Yoshiki ItoMotor Skills Instruction
Instruction Stacking Collapse: A Benchmark and the Capability-Dependent Value of Prompt Compilation
Jul 31, 2026Atul Anand, Sourav ChattarajInstruction-Tuned Models Instruction
IFHierBench: Hierarchical Instruction Following for Large Language Models
Jul 30, 2026Yuetian Mao, Chunyang ChenInstruction-Tuned Models Instruction
Steering Instruction Hierarchies at Inference Time
Jul 28, 2026Siqi Zeng, Sewoong Lee, Han Zhao +1Instruction-Tuned Models Training-Free Inference Framework
Interactive Reward Agent: GUI Task Evaluation via Environment-State Verification
Jul 28, 2026Chenrui Shi, Yuwei Wu, Yang Liu +5Graphical User Interface Agents Graphical User Interface
IKS-Instruct: A 24,000-Example Multilingual Dataset for Teaching Language Models Indian Knowledge Systems
Jul 25, 2026Shwetha Singaravelu, Gayathri Muruganantham, Lakshmi Rajendran +1Instruction Instruction-Tuned Models
Task Competence Is Not Instruction Following: Evaluating Instruction-Conflicting Behavior in Small Language Models
Jul 21, 2026Mahdiyeh Farajidizaji, Vatsal RainaInstruction-Tuned Models Instruction
From Trajectories to Instructions: Language-Conditioned Meta-Reinforcement Learning
Jul 21, 2026Garvit Singla, Uma Maheswari Natarajan, Raghuram Bharadwaj DiddigiMeta-Learning Instruction
Learning from Synthetic Data without Model Collapse in Iterative Instruction Tuning
Jul 19, 2026Xiaonan Luo, Yue Huang, Kehan Guo +4Instruction Tuning Synthetic Training Data
ReBind: Multi-Reference Video Editing via Structured Instructions with Explicit Reference Relationships
Jul 16, 2026Xinyu Liu, Shihao Li, Weihong Lin +10Video Editing Text-To-Video Models
VGIF-Score: Interpretable and Diagnostic Evaluation of Spatio-Temporal Instruction Following in Video Generation
Jul 15, 2026Songyu Xu, Xin Wang, Qiang Chen +6Instruction Temporal Dependence
Improving Text-to-Audio Instruction Following via Fine-Grained Feedback from Audio-Aware Large Language Models
Jul 15, 2026Chun-Yi Kuan, Siwon Kim, Byeonggeun Kim +7Large Audio Language Models Instruction
Instruction Set and Language for Hypergraphs
Jul 11, 2026Mario Pascual-Gonzalez, Ezequiel Lopez-RubioHypergraphs Instruction
Index SLM Technical Report
Jul 10, 2026Lusheng Zhang, Shien He, Tianxing Yan +5Small Language Models Instruction
Scoped Verification for Reliable Long-Horizon Agentic Context Evolution under Distribution Shift
Jul 10, 2026Dan C. Hsu, Luke LuLong-Horizon Agents Large Language Model Agents
Grounding Spatial Relations in a Compact World Model: Instruction Leakage and a Goal-Free Dynamics Fix
Jul 8, 2026Yufeng Wang, Lu Wei, Haibin LingContextual Grounding Instruction
HiFuzz: Hierarchical Reinforcement Learning for Semantic-Aware and Adaptive CPU Fuzzing
Jul 7, 2026Ya Wang, Hanwei Fan, Zhenguo Liu +4Fuzzing Risc-V
NAVER LABS System Re-implementation for the IWSLT 2026 Instruction-Following Task
Jul 6, 2026Anand Kamble, Aniket TatheSpeech Encoder Instruction
Path-level Hindsight Instructions for Semantic Exploration in Vision-Language Navigation
Jul 2, 2026Sung June Kim, Sangpil Kim, Honglak LeeVision-Language Navigation Hindsight
Indi-RomCoM: Code-Mixed Benchmark for Evaluating LLMs on Romanized Indic-English Instructions
Jun 29, 2026Avisha Das, Mihir Parmar, Mohana Ramnath +1Multilingual Benchmark Multilingual
Neural Procedural Memory: Empowering LLM Agents with Implicit Activation Steering
Jun 29, 2026Chengfeng Zhao, Yuqiao Tan, Shizhu He +3Large Language Model Agents Agent Memory
Are Humans Evolved Instruction Followers? An Underlying Inductive Bias Enables Rapid Instructed Task Learning
Jun 29, 2026Anjishnu KumarInstruction Cognitive Science
Learning Complementary Action Modeling from Automotive Maintenance Instructions
Jun 26, 2026Jiaqi Wu, Bai Li, Jochen Hartmann +2Instruction Fine-Grained Actions
On the Inseparability of Instructions and Data in Shared-Embedding Sequence Models
Jun 25, 2026Dewank Pant, Shruti Lohani, Avijit KumarIndirect Prompt Injection Untrusted Input
TraMP-LLaMA: Generative Interpretability with Decoupled Instruction Tuning for Facial Expression Quality Assessment
Jun 25, 2026Shuchao Duan, Alan Whone, Hossein Rahmani +2Facial Expression Recognition Multimodal Evaluation
FBK's Long-form SpeechLLMs for IWSLT 2026 Instruction Following
Jun 25, 2026Zhihang Xie, Marco Gaido, Sara Papi +2Speech-Llms Instruction
NebulaExp-8B: An Empirical Post-Training Pipeline via Full-Scale Ablation Research
Jun 25, 2026Qiaobo Hao, Yangqian Wu, Shunyi Wang +5Large Language Model Post-Training LLM Post-Training Methods
Instruction Bleed: Cross-Module Interference in Prompt-Composed Agentic Systems
Jun 24, 2026Ching-Yu Lin, Yifan LiuAgentic Systems Multi-Turn Tool-Use Agent
Flatness Preserves Instruction Following in Vision-Language-Action Models
Jun 22, 2026Haochen Zhang, Yonatan BiskVision-Language Instruction
Low-Energy Reduced RISC-V Instruction Subset Processor for Tsetlin Machine Inference at the Edge
Jun 18, 2026Chanda Gupta, Sanidhya Bhatia, Shaurya Priyadarshi +3Risc-V Instruction
MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction
Jun 17, 2026Jianing Zhang, Chenhao Zheng, Yajun Yang +10Human Motion Prediction 3D Motion
DRIFT: Refining Instruction Data via On-Policy Data Attribution
Jun 16, 2026Zefan Wang, Lincheng Li, Tianyu Yu +1Supervised Fine-Tuning Reinforcement Fine-Tuning
Distilling Examples into Task Instructions: Enhanced In-Context Learning for Real-World B2B Conversations
Jun 14, 2026Guy Rotman, Adi Kopilov, Danit Berger Zalmanson +1In-Context Learning Few-Shot Learning
Toward Instructions-as-Code: Understanding the Impact of Instruction Files on Agentic Pull Requests
Jun 11, 2026Ali Arabat, Mohammed SayaghCoding Agents Software Engineering
Training LLMs to Enforce Multi-Level Instruction Hierarchies via Gravity-Weighted Direct Preference Optimization
Jun 9, 2026Lena S. Bolliger, Lena A. JägerLarge Language Model Alignment Instruction-Tuned Models
Which LoRA? An Empirical Study on the Effectiveness of LoRA Techniques During Multilingual Instruction Tuning
Jun 9, 2026Thamali Wijewardhana, Napoleon H. Reyes, Surangika RanathungaMultimodal Instruction Tuning Multilingual
Instruction Finetuning DeepSeek-R1-8B Model Using LoRA and NEFTune
Jun 9, 2026Wu Yuerong, Mingni LuoNamed-Entity Recognition Large Language Model Fine-Tuning
When Built-in Thinking Helps and Hurts: Constraint-Level Error Shifts in Instruction Following
Jun 8, 2026Sai Adith Senthil KumarLarge Reasoning Models Thinking
PRISM: Recovering Instruction Sets from Language Model Activations
Jun 8, 2026Gilad Gressel, Rahul Pankajakshan, Julia Diament +3Instruction-Tuned Models Instruction
OmniCap-IF: Benchmarking and Improving Instruction Following Abilities for Omni-Video Captioning
Jun 7, 2026Jiahao Wang, An Ping, Yanghai Wang +13Omni-Modal Video Captioning
VCIFBench: Evaluating Complex Instruction Following for Video Understanding
Jun 3, 2026Huangchen Xu, Yuan Wu, Yi ChangVideo Understanding Instruction
Bootstrap Your Generator: Unpaired Visual Editing with Flow Matching
Jun 2, 2026Yoad Tewel, Yuval Atzmon, Gal Chechik +1Video Editing Image Editing
Bridging Auxiliary Constraints to Resolve Instruction Following in Large Reasoning Models
Jun 2, 2026Zhengyi Zhao, Shubo Zhang, Huimin Wang +7Label Constraint Modeling Large Reasoning Models

Sep 14, 2026 · cs.ROJ/K move · Enter open · S save

C $^2$ Nav: Compare Before You Commit for Zero-Shot Vision-and-Language Navigation

Runtian Zheng, Congpeng Zhang, Ying Liu

North China University of Technology, Beijing, China

Zero-shot vision-and-language navigation in continuous environments (VLN-CE) increasingly places foundation vision-language models (VLMs) inside the navigation loop. Existing systems commonly request cardinal outputs such as waypoints, pixels, headings, progress values, or absolute arrival decisions, coupling a generative response to geometric magnitude or an irreversible commitment. We study a complementary model-robot interface: the VLM compares controller-constructed alternatives, while geometry, thresholds, action magnitude, and execution remain on the physical side. We instantiate this idea in C2Nav, a training-free framework with three coordinated faculties. Seeing performs ordinal Gaze Election over physically vetted candidate views; Remembering maintains a compact route sketch and compares adjacent instruction-leg hypotheses; and Arriving combines a hesitation ladder, look-back comparison, and revocable walk-back for reliable stopping. On the public OpenNav R2R-CE 100 protocol, C2Nav with Qwen3-VL-8B-Instruct obtains 41.0% OSR, 31.0% SR, and 16.7% SPL, while the same interface with the standard GPT-5.5 model reaches 54.0% OSR, 44.0% SR, and 29.0% SPL. Whole-faculty ablations reduce SR to 14.0% without Seeing, 25.0% without Remembering, and 29.0% without Arriving. Matched role inversions that replace only the comparative answer form with cardinal/absolute questions reduce SR to 12.0%, 28.0%, and 21.0% in the spatial, transition, and terminal slots, respectively. The results indicate that a constrained decision interface and stronger VLM reasoning are complementary rather than interchangeable.

Vision-Language Navigation Navigation Large Vision Language Models Instruction

Open paper Ask about it PDF