Interpretable Attribute Control
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Latent Space Disentanglement via Activation Steering for Interpretable Attribute Control in Symbolic Music Generation
new Abstract: Transformer-based architectures have significantly advanced the generation of complex symbolic sequences, yet a significant gap remains in achieving fine-grained, interpretable control over discrete signal attributes. This paper investigates the mechanistic interpretability of the Multitrack Music Transformer (MMT) and proposes a framework for deterministic attribute modulation without retraining to bridge this gap via inference-time activation steering. Utilizing the...
Sparse Autoencoders for Interpretable Emotion Control in Text-to-Speech
arXiv:2606.01479v1 Announce Type: new Abstract: Integrating large language models (LLMs) into text-to-speech (TTS) systems has improved speech expressiveness, yet interpretable emotional control remains challenging. Existing approaches primarily rely on external conditioning or global activation steering, offering limited insight into the internal representations underlying emotional control.
SHAP-Guided Kernel Actor-Critic for Explainable Reinforcement Learning
arXiv:2512.05291v3 Announce Type: replace Abstract: Actor-critic (AC) methods are a cornerstone of reinforcement learning (RL) but offer limited interpretability. Current explainable RL methods seldom use state attributions to assist training. Rather, they treat all state features equally, thereby neglecting the heterogeneous impacts of individual state dimensions on the reward.
AnchorSteer: Self-Discovered Concept Injection for Structure-Preserving Music Editing
arXiv:2605.31053v1 Announce Type: new Abstract: Controllable music editing is to modify high-level attributes while strictly preserving rhythmic and melodic structures. However, this task is challenged by a semantic-structural entanglement: steering methods often degrade structure to achieve editing performance, while structural adaptors suppress semantic responsiveness. We propose AnchorSteer, a framework that disentangles this tension by coupling structural anchoring with self-discovered...
Document-Authored Control-Signal Impersonation: A Low-Cost Indirect Prompt Attack on RAG Safety Boundaries
arXiv:2606.09005v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) systems often serialize user queries, retrieved documents, metadata, system labels, and task instructions into one natural-language prompt. We study a source-authority boundary failure in this design: attacker-authored retrieved text can impersonate metadata, provenance, authority, or disclosure-policy signals that appear control-relevant to the model. We call this pattern Document-Authored Control-Signal...
Ahoy, DECmate II the little PDP-8 that could
Now, that's a lot of word processing. But under the hood it's still at least PDP-8 adjacent, even considering its oddities and incompatibilities, and you can make it do many of the things a full-size Eight can. We'll take this basic unit, convert the floppy drives to solid state, tap the video output, and put it through its paces.
GoodVibe: Security-by-Vibe for LLM-Based Code Generation
arXiv:2602.10778v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used for code generation in fast, informal development workflows, often referred to as vibe coding, where speed and convenience are prioritized, and security requirements are rarely made explicit. In this setting, models frequently produce functionally correct but insecure code, creating a growing security risk. Existing approaches to improving code security rely on full-parameter fine-tuning or...
SpeakerCard-1M: An Evidence-Grounded Speaker Card Corpus for In-the-Wild Speaker Verification
arXiv:2606.03283v1 Announce Type: cross Abstract: Modern speaker verification (SV) systems rely on speaker embeddings that are effective but difficult to interpret or query in natural language. Most existing speech-text corpora target controllable synthesis or utterance-level captioning, and provide limited speaker-level supervision for in-the-wild speaker recognition. This paper introduces SpeakerCard-1M, a bilingual speaker-centric resource for evidence-grounded SV, derived from...
SpeakerCard-1M: An Evidence-Grounded Speaker Card Corpus for In-the-Wild Speaker Verification
Announce Type: replace-cross Abstract: Modern speaker verification (SV) systems rely on speaker embeddings that are effective but difficult to interpret or query in natural language. Most existing speech-text corpora target controllable synthesis or utterance-level captioning, and provide limited speaker-level supervision for in-the-wild speaker recognition. This paper introduces SpeakerCard-1M, a bilingual speaker-centric resource for evidence-grounded SV, derived from VoxCeleb1/2 and...
Temporal Preference Concepts and their Functions in a Large Language Model
Announce Type: new Abstract: Large Language Models (LLMs) are increasingly being deployed to make decisions that require trading off near-term gains against long-term consequences, yet little is known about how they internally represent or resolve these tradeoffs. In this work, we causally localize an underlying subgraph for temporal preference in a distilled LLM (Qwen3-4B-Instruct-2507), identifying mid-to-upper-layer nodes through converging evidence from gradient-based attribution and...