arXiv Machine Learning
Aug 5
Sparse Weight Decomposition for Efficient Circuit Extraction
arXiv:2608. 03913v1 Announce Type: new Abstract: Dense pretrained transformers do not naturally expose interpretable units for circuit extraction.
Benchmarks and evaluation
Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv Machine Learning
Aug 5
Latent Reward Registers for Diffusion Preference Alignment
arXiv:2608. 03929v1 Announce Type: new Abstract: Aligning diffusion models with human preferences usually relies on a sparse terminal reward evaluated on the final generated samples, presenting a severe temporal credit-assignment challenge across the multi-step denoising process.
arXiv Machine Learning
Aug 5
DP-MemView: A Memory Interface for Attribute-Level Transcript Privacy in Long-Term LLM Agents
arXiv:2608. 03130v1 Announce Type: cross Abstract: Long-term memory enables persistent personalization in LLM agents, but repeated memory-conditioned responses can cumulatively reveal protected attributes even when they are never stated explicitly.
arXiv Machine Learning
Aug 5
Conformal risk control for model-form uncertainty in parametric non-intrusive reduced-order models
arXiv:2608. 03360v1 Announce Type: cross Abstract: Non-intrusive reduced-order models (NIROMs) have become a standard tool for approximating parametric partial differential equations from computer design of experiments while significantly reducing computational costs.
arXiv Machine Learning
Aug 5
Dynamically Allocating Evaluation Effort for Model Ranking
arXiv:2608. 03437v1 Announce Type: cross Abstract: While human evaluation is the gold standard in many NLP tasks, it suffers from prohibitive costs and poor scalability.
arXiv Machine Learning
Aug 5
SimulRAG: Simulator-based RAG for Grounding LLMs in Long-form Scientific QA
arXiv:2509. 25459v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) show promise in generating long-form scientific explanations that synthesize evidence and connect multiple factors.
arXiv Machine Learning
Aug 5
Design Criteria for SGD Preconditioners: Local Conditioning, Noise Floors, and Basin Stability
arXiv:2511. 19716v3 Announce Type: replace-cross Abstract: Stochastic Gradient Descent (SGD) often slows in the late stage of training due to anisotropic curvature and gradient noise.
arXiv AI
Aug 5
Beyond the Hivemind: Escaping LLM Homogeneity via Meta-Persona Anchoring and Sequential Temperature Scaling
arXiv:2608. 02618v1 Announce Type: new Abstract: Recent studies have identified an ``Artificial Hivemind'' effect in Large Language Models (LLMs) causing models to converge on a narrow, homogenized consensus even for open questions.
arXiv AI
Aug 5
ProPRL: Property-Aware Prerequisite Relation Learning in Educational Knowledge Graphs
arXiv:2608. 03006v1 Announce Type: new Abstract: Prerequisite relation learning is central to adaptive instruction, yet existing methods often formulate it as conventional link prediction, limiting their ability to adaptively integrate complementary educational evidence for individual candidate pairs and to discourage contradictory reverse predictions.
arXiv AI
Aug 5
Unequal Verdicts: Investigating Gender Bias in LLM-Based Fake News Detection
arXiv:2608. 03627v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used for automated fact-checking, yet their susceptibility to gender bias in this context remains underexplored.
arXiv AI
Aug 5
Pivot-Centric Trajectory Prediction: Bridging Long Horizons via Dynamical Guidance
arXiv:2608. 03521v1 Announce Type: cross Abstract: Forecasting precise future motion of surrounding agents is essential for reliable autonomous vehicles.
arXiv AI
Aug 5
Multi-Task Multi-Frame Visual Piano Transcription
arXiv:2608. 03419v1 Announce Type: cross Abstract: Audio-based piano transcription performs well on onset, pitch, and velocity, but the sustain pedal lets sound persist long after key release, so audio systems predict pedal-extended offsets rather than physical key release.
arXiv AI
Aug 5
A Theory of Conditional Collapse under Low-Rank Weight-Space Ablations: I. The Single-Block Theory and Synthetic Validation
arXiv:2608. 03620v1 Announce Type: cross Abstract: Activation patching and weight-space ablation both claim a component is causally responsible for a behavior, yet they act on different objects: one forward pass versus the parameters behind every forward pass.
arXiv AI
Aug 5
Failure-Informed Image Self-Augmentation for Multimodal Large Language Model Self-Improvement
arXiv:2608. 03733v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have achieved remarkable performance across vision-language tasks, but their progress depends heavily on large-scale, high-quality multimodal data that are costly to annotate.
arXiv AI
Aug 5
Diversity is Not Ambiguity: Toward Accurate and Efficient Ambiguity Detection for Open-Domain QA
arXiv:2608. 03177v1 Announce Type: new Abstract: How can question answering (QA) systems determine whether a query is ambiguous?
arXiv AI
Aug 5
Distractor-Aware Truncation: Disentangling Context-Length Effects from Signal Loss in Long-Context LLM Benchmarks
arXiv:2608. 03297v1 Announce Type: new Abstract: A standard claim in the literature on retrieval-augmented and memory-augmented language models is that shorter context is better when the relevant information is preserved.
arXiv AI
Aug 5
Large language models for partial differential equation workflows
arXiv:2608. 03600v1 Announce Type: new Abstract: Partial differential equations (PDEs) become actionable in science and engineering not as isolated formulae, but as executable workflows that connect modelling assumptions, governing equations, numerical solvers, diagnostics, and decisions.
arXiv AI
Aug 5
Taming the Implicit: Dual-Channel Risk-Aware Reinforcement Fine-Tuning for Continual Multimodal Post-Training
arXiv:2608. 03660v1 Announce Type: new Abstract: Reinforcement fine-tuning (RFT) is widely believed to inherently resist catastrophic forgetting in continual post-training of multimodal large language models.
arXiv AI
Aug 5
GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks
arXiv:2608. 03764v1 Announce Type: new Abstract: Agent self-evolution updates an agent's persistent state from prior experience and reuses it to solve related tasks more effectively.
arXiv AI
Aug 5
MemArena: An Ego-Centric Benchmark for On-Device Agentic Personal Memory Assistants at Scale
arXiv:2608. 02613v1 Announce Type: cross Abstract: Edge-deployed personal memory assistants must handle private interpersonal conversations on-device with open-weight models.