Target Decoupling
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks
arXiv:2602.02763v3 Announce Type: replace Abstract: Interpretable time series deep learning systems are often assessed by checking temporal consistency on explanations, implicitly treating this as evidence of robustness. We show that this assumption can fail: Predictions and explanations can be adversarially decoupled, enabling targeted misclassification while the explanation remains plausible and consistent with a chosen reference rationale. We propose TSEF (Time Series Explanation Fooler),...
How Do Document Parsers Break? Auditing Structural Vulnerability in Document Intelligence
arXiv:2605.19309v3 Announce Type: replace Abstract: Document Layout Analysis (DLA) pipelines provide structured page representations for retrieval-augmented generation, long-document question answering, and other document intelligence systems, yet their robustness evaluation remains largely area-centric. We identify this Footprint Bias and propose ProSA, a lightweight output-level auditing framework that decouples controlled probing, policy-driven targeting, and structure-aware diagnosis....
Representation over Routing: Diagnosing Temporal Routing Pathologies in Multi-Timescale PPO
Announce Type: replace Abstract: Temporal credit assignment in reinforcement learning is often approached by introducing value estimates at multiple discount factors. A natural next step is to let the actor dynamically route among these temporal heads, using either differentiable attention or heuristic uncertainty weights. This paper argues that such routing can create a numerical shortcut rather than a reliable temporal abstraction.
What to Format and How: A Benchmark and Workflow Approach for Document Formatting
Announce Type: new Abstract: Recent advances in large language models (LLMs) have opened up new possibilities for automated document formatting. However, real-world formatting often requires identifying targets based on document content. This content-aware setting remains challenging and underexplored, primarily due to the lack of dedicated evaluation datasets.
Bad Seeing or Bad Thinking? Rewarding Perception for Multimodal Reasoning
Announce Type: replace Abstract: Achieving robust perception-reasoning synergy is a central goal for advanced Vision-Language Models (VLMs). Recent advancements have pursued this goal via architectural designs or agentic workflows. However, these approaches are often limited by static textual reasoning or complicated by the significant compute and engineering burden of external agentic complexity.
Learning Terrain-Aware Whole-Body Control for Perceptive Legged Loco-Manipulation
arXiv:2605.31343v1 Announce Type: new Abstract: Legged manipulators integrate exceptional terrain adaptability along with mobile manipulation capabilities, which make them highly promising for deployment in human-centric environments. By coordinating the control of both legs and arms, a whole-body controller can significantly expand the operational workspace of legged manipulators. However, many existing whole-body controllers primarily depend on proprioception and do not incorporate the...
Demographic history, geographic distance, and landscape features shape the genetic divergence of wild tigers in northeast India
Habitat fragmentation creates small, isolated populations that are vulnerable to inbreeding, genetic drift, and a high genetic load. For conservation management, it is essential to distinguish contemporary landscape resistance from historical demographic processes as drivers of these genetic patterns, especially for conservation priority regions such as northeast India, which intersects two major tigers conservation landscapes. We studied the genetic structure and landscape connectivity of...
Once-For-All: A Train-Once and Select-Anytime Framework for Multimodal Instruction Tuning
arXiv:2605.26761v2 Announce Type: replace Abstract: Multimodal instruction tuning is the de facto recipe for adapting vision language models (VLMs), yet instruction data are highly redundant, making data selection critical for training efficiency. Existing methods derive selection signals from a specific model or dataset, so whenever the target model or candidate pool changes, the criteria must be recomputed from scratch at substantial cost. To address this, we propose OFA, a data selection...
Closure-Validated Circuit Discovery in Attention Heads: Co-activation Proposes, Ablation Disposes
arXiv:2606.09607v1 Announce Type: new Abstract: Interpretability increasingly treats groups of components, not individual units, as the basic object, and proposes to find them by clustering co-activation statistics. We ask whether such a cheap signal actually identifies an attention-head circuit. Adapting a sparse-autoencoder clustering recipe to attention heads -- but validating by causal ablation rather than reconstruction -- we cluster heads and then run a closure test: ablate the...
AlphaToken: Decoupling Adaptation and Stability for Path-Aware Response Token Valuation in LLM Post-Training
Announce Type: new Abstract: Token selection is pivotal for effective LLM post-training. However, existing methods mostly rely on local heuristics and rarely formulate token selection as a principled valuation of individual response tokens.