Hidden States

Follow this topic Ask about this topic

Recent momentum

-36%

9 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

2 new papers

A weekly snapshot of new work published in Hidden States.

Period ending 2026-09-14

2 new papers

A weekly snapshot of new work published in Hidden States.

Period ending 2026-09-07

7 new papers

A weekly snapshot of new work published in Hidden States.

107 papers

Latest in Hidden States

Browse all topics →

A Negative Result on Cross-Model Activation Transfer in a Pythia Multi-Hop Setting
Jun 2, 2026Peiyan Zhang, Jason XinModel Activations Hidden States
Linear Probes Detect Task Format, Not Reasoning Mode in Language Model Hidden States
Jun 1, 2026Subramanyam Sahoo, Vinija Jain, Aman Chadha +1Hidden States Mechanistic Interpretability
MLLM-Microscope: Unlocking Hidden Structure Within Multimodal Large Language Models
May 30, 2026Ravil Mussabayev, Rustam MussabayevMulti-Modal Large Language Models Multimodal Transformers
Hallucination Is Linearly Decodable from Mid-Layer Hidden States in Quantized LLMs
May 30, 2026Aizierjiang AiersilanHidden States Large Language Model Quantization
What Am I Missing? Question-Answering as Hidden State Probing
May 29, 2026Chu Fei Luo, Samuel Dahan, Xiaodan ZhuLarge Language Model Reasoning Closed-Book Question Answering
Minimal Prompt Perturbations Lead to Code Vulnerabilities: Prompt Fragility and Hidden-State Signals in Coding LLMs
May 28, 2026Alexander Sternfeld, Andrei Kucharavy, Ljiljana DolamicVulnerable Code Vulnerability Detection & Repair
Learning to Perturb Hidden Representations for Generalizable Deep Learning
May 28, 2026Hua LiPerturbations Hidden States
The Attentional White Bear Effect in Transformer Language Models
May 27, 2026Rebecca Ramnauth, Brian ScassellatiTransformer Architectures Hidden States
Single-Rollout Hidden-State Dynamics for Training-Free RLVR Data Selection
May 27, 2026Jianghao Wu, Jianfei Cai, Weiqiang Wang +3Reinforcement Learning With Verifiable Reward Verifiable Rewards
Can LLMs Introspect? A Reality Check
May 25, 2026Shashwat Singh, Tal Linzen, Shauli RavfogelIntrospection Adapters Metacognition
Adversarial Orthogonal Disentanglement for LVLM Hallucination Mitigation
May 25, 2026Ruoxi Cheng, Haoxuan Ma, Zhengfei Hai +6Large Language Model Hallucination Large Vision Language Models
Revisiting Pre-Propagation GNNs: Robust Diffusion Operators and Hidden-State Re-Propagation
May 24, 2026Zichao Yue, Zhiru ZhangGraph Neural Networks Propagation
Hidden-State Privacy Has an Empty Middle
May 21, 2026Alexander Okezue BellEfficient Privacy Loss Hidden States
The Hidden Signal of Verifier Strictness: Controlling and Improving Step-Wise Verification via Selective Latent Steering
May 20, 2026Yefan Zhou, Yilun Zhou, Austin Xu +3Verifier Few-Step
RSD: Moving Local Triangular Charts for Auditing Language-Model Hidden States
May 17, 2026Seungmin JinHidden States Algorithm Auditing
PARALLAX: Separating Genuine Hallucination Detection from Benchmark Construction Artifacts
May 16, 2026Khizar Hussain, Murat KantarciogluHallucination Detection Hallucinations
Representation Without Reward: A JEPA Audit for LLM Fine-Tuning
May 14, 2026Biswa SenguptaLarge Language Model Fine-Tuning Joint-Embedding Predictive Architectures
Probabilistic Verification of Recurrent Neural Networks for Single and Multi-Agent Reinforcement Learning
May 14, 2026Luca Marzari, Enrico MarchesiniReinforcement Learning With Verifiable Reward Deep Reinforcement Learning
Where Should Diffusion Enter a Language Model? Geometry-Guided Hidden-State Replacement
May 14, 2026Injin Kong, Hyoungjoon Lee, Yohan JoDiffusion Language Models Autoregressive Transformers
Steer-to-Detect: Probing Hidden Representations for Detection of LLM-Generated Texts
May 13, 2026Luxu Liang, Xiang LiMachine-Generated Text Detection Language Model Evasion Attacks
Deep Minds and Shallow Probes
May 12, 2026Su Hyeong Lee, Risi KondorImplicit Neural Representations Hidden States
Uniform Scaling Limits in AdamW-Trained Transformers
May 11, 2026William Gibson, Christoph ReisingerTransformer Architectures Hidden States
Dynamic Mode Decomposition along Depth in Vision Transformers
May 8, 2026Nishant Suresh Aswani, Saif Eddin JabariSelf-Supervised Vision Transformers Vision Transformer
CKT-WAM: Parameter-Efficient Context Knowledge Transfer Between World Action Models
May 7, 2026Yuhua Jiang, Yijun Guo, Hongbing Yang +7Efficient World-Action Model Faster-Wam
CRAFT: Forgetting-Aware Intervention-Based Adaptation for Continual Learning
May 7, 2026Md Anwar Hossen, Fatema Siddika, Juan Pablo Munoz +2Catastrophic Forgetting Large Language Model Adaptation
Attractor Geometry of Transformer Memory: From Conflict Arbitration to Confident Hallucination
May 7, 2026Qiyao Liang, Risto Miikkulainen, Ila FieteLarge Language Model Hallucination Hidden States
Neural Co-state Policies: Structuring Hidden States in Recurrent Reinforcement Learning
May 6, 2026David Leeftink, Max Hinne, Marcel van GervenLatent States Hidden States
How Long Does Infinite Width Last? Signal Propagation in Long-Range Linear Recurrences
May 6, 2026Mariia SeleznovaInfinite-Width Gaussian Limit Scaling Laws
Where Reliability Lives in Vision-Language Models: A Mechanistic Study of Attention, Hidden States, and Causal Circuits
May 5, 2026Logan Mann, Ajit Saravanan, Ishan Dave +4Vision-Language Hidden States
Stable Blanket with Hidden Variables and Cycles
May 3, 2026Hanqing XiangCausal Graph Latent Variable
Spatiotemporal Hidden-State Dynamics as a Signature of Internal Reasoning in Large Language Models
May 3, 2026Kotaro Furuya, Takahito TanimuraEfficient Latent Reasoning Hidden States
From Backward Spreading to Forward Replay: Revisiting Target Construction in LLM Parameter Editing
May 1, 2026Wei Liu, Hongkai Liu, Zhiying Deng +2Multimodal Knowledge Editing Large Language Model Backbones
When Hidden States Drift: Can KV Caches Rescue Long-Range Speculative Decoding?
Apr 29, 2026Tianyu Liu, Yuhao Shen, Xinyi Hu +8Speculative Decoding Kv-Cache Blocks
HIVE: Hidden-Evidence Verification for Hallucination Detection in Diffusion Large Language Models
Apr 28, 2026Guoshenghui Zhao, Tan Yu, Weijie ZhaoHallucination Detection Hallucination Rate
Subliminal Steering: Stronger Encoding of Hidden Signals
Apr 28, 2026George Morgulis, John HewittImplicit Bias Hidden States
When Chain-of-Thought Fails, the Solution Hides in the Hidden States
Apr 25, 2026Houman Mehrafarin, Amit Parekh, Ioannis KonstasChain-of-Thought Reasoning Reasoning Traces
Hidden States Know Where Reasoning Diverges: Credit Assignment via Span-Level Wasserstein Distance
Apr 25, 2026Xinzhu Chen, Wei He, Huichuan Fan +7Credit Assignment Group Relative Policy Optimization
There Will Be a Scientific Theory of Deep Learning
Apr 23, 2026Jamie Simon, Daniel Kunin, Alexander Atanasov +11Learning Dynamics Deep Learning
Mitigating Hallucinations in Large Vision-Language Models without Performance Degradation
Apr 22, 2026Xingyu Zhu, Junfeng Fang, Shuo Wang +4Large Language Model Hallucination Hallucination Mitigation
ATLAS: Constitution-Conditioned Latent Geometry and Redistribution Across Language Models and Neural Perturbation Data
Apr 19, 2026Gareth Seneque, Lap-Hang Ho, Nafise Erfanian Saeedi +2Atlas Representational Geometry
Learning Uncertainty from Sequential Internal Dispersion in Large Language Models
Apr 17, 2026Ponhvoan Srey, Xiaobao Wu, Cong-Duy Nguyen +1Large Language Model Uncertainty Hallucination Detection
Self-Routing: Parameter-Free Expert Routing from Hidden States
Apr 1, 2026Jama Hussein Mohamud, Drew Wagner, Mirco RavanelliMixture-of-Experts Models Expert Routing
ReLope: KL-Regularized LoRA Probes for Multimodal LLM Routing
Mar 25, 2026Yaopei Zeng, Congchao Wang, Blake JianHang Chen +1Large Language Model Routing Multi-Modal Large Language Models
How Transformers Reject Wrong Answers: Rotational Dynamics of Factual Constraint Processing
Feb 25, 2026Javier MarínTransformer Encoder Transformer Architectures
LLMs Can't Play Hangman: On the Necessity of a Private Working Memory for Language Agents
Jan 11, 2026Davide Baldelli, Ali Parviz, Amal Zouaq +1Multilingual Agents Agent Memory
Hidden State Poisoning Attacks against Mamba-based Language Models
Jan 5, 2026Alexandre Le Mercier, Chris Develder, Thomas DemeesterLanguage Model Evasion Attacks Bidirectional Mamba
You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations
Nov 9, 2025Amit LeVi, Raz Lapid, Rom Himelstein +3Weight-Only Quantization Quantization

Jun 2, 2026 · cs.AIJ/K move · Enter open · S save

A Negative Result on Cross-Model Activation Transfer in a Pythia Multi-Hop Setting

Peiyan Zhang, Jason Xin

Independent Researcher

Recent work shows that language models can transmit behavioural traits through hidden signals in generated data during training. We ask whether a different activation-mediated channel is viable: can one language model communicate a useful intermediate reasoning state to another at inference time through a post-hoc linear activation bridge, rather than through a textual or structured-token relay? We test this question in a controlled Pythia-160M to Pythia-410M multi-hop reasoning setting. A linear translation layer learns a strong normalized-space map between sender and receiver hidden states, with normalized cosine similarity near 0.97 across seeds. However, when the translated activations are injected into the receiver at inference time, they do not improve downstream answering. Low-strength additive injection remains near the no-injection baseline, with confidence intervals that cross zero. Replacement-style injection is consistently destructive, and rescaling translated vectors to the receiver hidden-state norm does not rescue performance. The result is therefore a scoped negative result: in this setting, offline representational alignment is not sufficient for useful causal communication inside the receiver.

Model Activations Hidden States Multi-Hop Reasoning Activation Functions

Open paper Ask about it PDF