Latent Trajectories

Follow this topic Ask about this topic

Recent momentum

+0%

4 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 2026-09-14

1 new paper

A weekly snapshot of new work published in Latent Trajectories.

Period ending 2026-09-07

3 new papers

A weekly snapshot of new work published in Latent Trajectories.

40 papers

Latest in Latent Trajectories

Open your feed →

Do Agents Know When They Succeed? Calibrating Agent Confidence from Internal Representations
Sep 10, 2026Priyanka Mary Mammen, Emil Joswin, Srujananjali MedicherlaAgentic Systems Confidence Calibration
From Final Artifacts to Trajectories: Retrospective Process Supervision for Evidence-Grounded Long-Form Generation
Aug 31, 2026Junjie Huang, Jiarui Qin, Di Yin +4Latent Trajectories Content Provenance
Tracing Generated Samples to Training-Data Clusters in Flow-Matching Models
Aug 30, 2026Rania Briq, Ohad Fried, Michael Kamp +1Generative Models Velocity Field
LLMODE: Aligning ODEs with LLMs via Gated Token Injection for Irregular Spatio-Temporal Forecasting
Aug 30, 2026Di Zhang, Jingyang Zhang, Ziqian Wang +4Spatio-Temporal Forecasting Latent Trajectories
When Latents Forget Pixels: Restoring Fidelity in Diffusion Transformer Super-Resolution
Aug 10, 2026Yu Shi, Yuyao Zhang, Yu-wing TaiGenerative Super-Resolution Low-Resolution
Stable Density Ridges: Consistency and Convergence of Subspace Constrained Mean Shift
Aug 5, 2026Wanli QiaoDensity Ratio Estimation Maximum Mean Discrepancy
GASP: GPU-Accelerated Safe Planner for Real-Time Collision-Aware Motion Generation with Latent Trajectory Sampling
Aug 5, 2026Colin Merk, Stefanos Charalambous, Peter Dürr +1Collision-Free Trajectories Trajectory Optimization
LUT: Latent Utility Training for Visual Reasoning
Aug 1, 2026Jiaxuan Kang, Siyu Chen, Mingda Li +6Latent Visual Reasoning Visual Reasoning
CLDRoute: Conditional Latent Diffusion for Routability Map Generation in Physical Design
Jul 18, 2026Kiran Thorat, Nicole Meng, Caiwen Ding +2Expert Routing Identity-Conditioned Latent Diffusion Models
Latent Trajectory Discrimination for AI-Generated Text Detection
Jul 16, 2026Gianluca Bonifazi, Christopher Buratti, Michele Marchetti +5Machine-Generated Text Detection Latent Trajectories
From Jumps to Signatures: a Generative Method for Temporal Point Processes
Jul 7, 2026Niels Cariou-Kotlarek, Vasileios LamposDeterminantal Point Process Synthetic Time Series
Handwriting Trajectory Recovery with Diffusion Models
Jul 3, 2026Hiroki Nagamatsu, Shoji Toyota, Seiichi UchidaHandwritten Text Recognition Latent Trajectories
SemRF: A Semantic Reference Frame for Residual-Stream Dynamics in Language Models
Jun 30, 2026Jian Gu, Aldeida Aleti, Chunyang Chen +1Residual Stream Latent Trajectories
Invariant Reasoning Directions in Latent Trajectories of Language Models
Jun 28, 2026Arun Vignesh Malarkkan, Manan Roy Choudhury, Utkarsh Byahut +3Reasoning Trajectory Latent Trajectories
Proposal-Conditioned Latent Diffusion for Closed-Loop Traffic Scenario Generation
Jun 25, 2026Shubham Vaijanath Phoolari, Aleyna Kara, Christoph Lauer +1Autonomous Driving Simulation Scenario Generation
BFMTrack: Latent Sequence Optimization for Physics-Based Motion Tracking with Behavioral Foundation Models
Jun 23, 2026Thomas Rupf, Agon Serifi, David Müller +4Latent Trajectories Motion Sequence
BayesFP: Posterior Estimation for Flow-Based Policies via Feynman-Kac Sampling
Jun 19, 2026Sreevardhan Sirigiri, Weiming Zhi, Fabio RamosFlow-Based Policy Diffusion Policies
PO-PDDL: Learning Symbolic POMDPs from Visual Demonstrations for Robot Planning Under Uncertainty
Jun 14, 2026Wenjing Tang, Xuanjin Jin, Yuan Liu +3Partially Observable Markov Decision Process Belief Space
ST-DiffEye: Diffusion-based Continuous Gaze Generation via Joint Scanpath-Trajectory Modeling
Jun 13, 2026Brian Nlong Zhao, Ozgur Kara, Junho Kim +1Gaze Generative Processes
Where Should Knowledge Enter? A Layered Framework for Knowledge Infusion in Multimodal Iterative Generative Model
Jun 4, 2026Renjith Prasad, Chathurangi Shyalika, Anushka Pawar +2Multimodal Generation Generative Processes
SAM-Flow: Source-Anchored Masked Flow for Training-Free Image Editing
Jun 4, 2026Haowang Cui, Rui Chen, Tao Luo +3Diffusion Editing Image Editing
The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show
Jun 3, 2026Parsa Esmati, Somjit Nath, Katja Hofmann +3Pre-Trained Video Diffusion Models Multimodal Diffusion Transformers
Conditional Latent Diffusion Model with Fourier-based Motion Modelling for Virtual Population Synthesis
Jun 2, 2026Shaokun Lan, Haoran Dou, Jinghan Huang +5Cardiac Motion Meshes
Latent Goal Prediction from Language for Model-Based Planning
May 26, 2026Samuel Barbeau, Simon Roy, Giovanni Beltrame +2Classical Planning Latent World Models
STORM: Internalized Modeling for Spatial-Temporal Reasoning in Video-Language Models
May 25, 2026Yiming Liang, Yixiao Chen, Yiyang Zhou +8Video-Language Models Video Understanding
Modeling Temporal scRNA-seq Data with Latent Gaussian Process and Optimal Transport
May 20, 2026Mehmet Yigit Balik, Harri LähdesmäkiSingle-Cell Rna Sequencing Gaussian Process
Generative Recursive Reasoning
May 19, 2026Junyeob Baek, Mingyu Jo, Minsu Kim +3Recursion Latent Trajectories
EviTrack: Selection over Sampling for Delayed Disambiguation
May 19, 2026Omer HaqLatent Trajectories Sequence Modeling
Latent Action Control for Reasoning-Guided Unified Image Generation
May 16, 2026Fuxiang Zhai, Sixiang Chen, Yingjin Li +4Image Generation Latent Actions
Compositional Video Generation via Inference-Time Guidance
May 14, 2026Ariel Shaulov, Eitan Shaar, Amit Edenzon +2Latent Trajectories Explanation Faithfulness
Privacy Evaluation of Generative Models for Trajectory Generation
May 14, 2026Stavros Bouras, Ioannis Kontopoulos, Chiara Pugliese +5Generative Models Latent Trajectories
Language Generation as Optimal Control: Closed-Loop Diffusion in Latent Control Space
May 14, 2026ZiYi Dong, Yuliang Huang, Weijian Deng +3Diffusion Language Models Stochastic Optimal Control
Vision-Based Runtime Monitoring under Varying Specifications using Semantic Latent Representations
May 13, 2026Bardh Hoxha, Oliver Schön, Hideki Okamoto +2Runtime Enforcement Partial Observability
Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models
May 12, 2026Kecheng Chen, Ziru Liu, Xijia Tao +9Diffusion Language Models Autoregressive Language Models
Slowly Annealed Langevin Dynamics: Theory and Applications to Training-Free Guided Generation
May 8, 2026Atsushi Nitanda, Dake Bu, Yueming Lyu +1Langevin Dynamics Latent Trajectories
NoisyCoconut: Counterfactual Consensus via Latent Space Reasoning
May 6, 2026Michael Jerge, David EvansLarge Language Model Reasoning Efficient Latent Reasoning
Tracing the Dynamics of Refusal: Exploiting Latent Refusal Trajectories for Robust Jailbreak Detection
May 2, 2026Xulin Hu, Che Wang, Wei Yang Bryan Lim +2Jailbreak Detection Refusals
MidSteer: Optimal Affine Framework for Steering Generative Models
Apr 17, 2026Tatiana Gaintseva, Andrew Stepanov, Ziquan Liu +4Steering Training-Free Reward Alignment
LLM Reasoning Is Latent, Not the Chain of Thought
Apr 17, 2026Wenshuo WangLarge Language Model Reasoning Latent Trajectories
Anomaly detection in time-series via inductive biases in the latent space of conditional normalizing flows
Mar 12, 2026David Baumgartner, Eliezer de Souza da Silva, Iñigo UrteagaTime-Series Anomaly Detection Anomaly Detection

Sep 10, 2026 · cs.AIJ/K move · Enter open · S save

Do Agents Know When They Succeed? Calibrating Agent Confidence from Internal Representations

Priyanka Mary Mammen, Emil Joswin, Srujananjali Medicherla

As agentic systems getting adopted rapidly in safety critical applications, it is vital to measure the confidence associated with the agentic actions. In comparison to the traditional machine learning systems, agentic workflows have complex failure modes with planning, tool invocation and dynamic environment interactions. In this paper, we investigate whether model's internal representations provide stronger signals of eventual task success in multi-turn agentic setups. We introduce two complementary methods: Latent Trajectory Dynamics (LTD), which summarizes changes in residual-stream representations across an an interaction trajectory, and the Action Representation Probe (ARP), which predicts success from representations formed at action decisions. Across three interactive benchmarks (Bash, SQL, Python) and three model families (Qwen14B, Qwen7B, DeepSeek6.7B), our methods consistently outperform surface level generation and sequence-based calibration baselines providing a zero-overhead reliability monitor that requires neither prompt alterations nor multi-sample rollouts.

Agentic Systems Confidence Calibration Latent Trajectories

Open paper Ask about it PDF