arXiv AI
Aug 17
BGA: A noise-immune neural distillation framework for malicious signature extraction in high-entropy encrypted flows
arXiv:2608. 14126v1 Announce Type: cross Abstract: To mitigate attention dilution in high-entropy TLS 1.
Benchmarks and evaluation
Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv AI
Aug 17
The Metacognitive Bottleneck: Japanese Riddles Reveal Fundamental Limits of Machine Insight and Self-Evaluation in Reasoning AI
arXiv:2509. 14704v3 Announce Type: replace Abstract: Benchmark saturation and training-data contamination increasingly obscure whether reported gains in large language models (LLMs) reflect genuine advances in reasoning or familiarity with recurring patterns in benchmark problems.
arXiv AI
Aug 17
EchoChange: A Diffusion Language Model with Dual Pass Remasking for Factual Remote Sensing Disaster Change Captioning
arXiv:2608. 01856v2 Announce Type: replace Abstract: Bi-temporal remote-sensing disaster change captioning often needs to identify sparse and spatially localized changes across large pre- and post-event scenes and then translate them into coherent, factual descriptions.
arXiv AI
Aug 17
MemoryLake on MemoryArena: A Matched Study of Agent Memory Backends
arXiv:2608. 13883v1 Announce Type: new Abstract: Most agent-memory benchmarks test post-hoc recall, whereas MemoryArena evaluates whether memory supports interdependent, multi-session task completion.
arXiv AI
Aug 17
A Graph-Based Reinforcement Learning Framework for Structured Drift Diagnosis and Recovery in Autonomous LLM Agents
arXiv:2608. 14109v1 Announce Type: new Abstract: Autonomous LLM agents are increasingly deployed in complex real-world workflows, yet they remain vulnerable to runtime behavioral drift, a silent deviation from the original task that can lead to irreversible side effects on external systems.
arXiv AI
Aug 17
Self-Supervised Visual On-Policy Distillation
arXiv:2608. 14144v1 Announce Type: cross Abstract: Visual on-policy distillation relies heavily on an informative teacher-student asymmetry, through either a larger, stronger teacher or privileged supervision, such as reference answers or ground-truth regions of interest.
arXiv AI
Aug 17
Fixed-Budget Gaussian Volume Encoding with Structure-Aware Allocation
arXiv:2608. 14112v1 Announce Type: cross Abstract: Scientific simulations often produce scalar volumes faster than they can be stored, transferred, and loaded, while in situ reduction must use only a limited share of simulation resources.
arXiv AI
Aug 17
SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation for Long-Context Reasoning
arXiv:2608. 14277v1 Announce Type: cross Abstract: On-policy distillation (OPD) offers a promising way to transfer reasoning capabilities from stronger teacher models, but applying it to long-context reasoning teachers and short-context students introduces practical challenges, including tokenizer mismatch, teacher-student distribution mismatch, response length explosion, and training instability.
arXiv AI
Aug 17
Generating Benchmark Health Data Using a Tabular Diffusion Transformer
arXiv:2608. 14496v1 Announce Type: cross Abstract: Cross-Tabular Data Generation (CTDG) seeks to learn a generative model from multiple heterogeneous tables and produce new synthetic tabular datasets.
arXiv AI
Aug 17
Parameter- and Bandwidth-Efficient Edge--cloud Many-to-Many Speech-to-Text Translation
arXiv:2605. 28642v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) have demonstrated significant potential for speech-to-text translation (S2TT).
arXiv Machine Learning
Aug 17
Language-Specific Gaps in AI Safety Training Datasets
arXiv:2608. 13695v1 Announce Type: cross Abstract: Large language model providers routinely cite multilingual safety benchmarks spanning a dozen or more languages as evidence that their models are safe for non-English-speaking users.
arXiv AI
Aug 17
Demystifying Agent Skills: Why They Work-Until They Don't
arXiv:2608. 14036v1 Announce Type: new Abstract: Skills have emerged as a practical and effective approach for enhancing LLM agents at inference time through structured packages of knowledge.
arXiv AI
Aug 17
Amplified Does Not Mean Predictive: Reasoning Behaviors in Thinking Models
arXiv:2608. 13760v1 Announce Type: cross Abstract: Which reasoning behaviors are associated with correct answers in reasoning models, and does reasoning-oriented training amplify those behaviors?
arXiv AI
Aug 17
GBU-Palm: A Multimodal Video Dataset and Benchmark for Palm Presentation Attack Detection
arXiv:2608. 14389v1 Announce Type: cross Abstract: Existing palm presentation attack detection (PAD) datasets are often limited by static imagery, restricted acquisition conditions, or insufficient multimodal video data, hindering systematic evaluation across environments, modalities, and attack types.
arXiv AI
Aug 17
Correcting What You Cannot See: Credit Assignment for Perception Distillation in Multimodal Reasoners
arXiv:2607. 28336v3 Announce Type: replace Abstract: On-policy distillation provides dense supervision for multimodal reasoners, but its trajectory-level reward cannot determine whether a failed answer arose from perception or subsequent reasoning.
arXiv AI
Aug 17
Depth-Aware Sensitivity Analysis of Mixture-of-Experts Models via Magnitude-Based Expert Masking
arXiv:2608. 13565v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures scale large language models (LLMs) while preserving computational efficiency through sparse activation.
arXiv AI
Aug 17
A Year in LLM Serving: Workload Evolution, Caching and Load-Balancing
arXiv:2608. 13573v1 Announce Type: new Abstract: Large Language Model (LLM) serving has become a critical cloud workload, and realistic traces are essential for motivating and benchmarking serving systems.
arXiv AI
Aug 17
MobileMem: Learning from a Year of Mobile Experiences
arXiv:2608. 13606v1 Announce Type: new Abstract: The next generation of AI agents is increasingly moving beyond systems that answer isolated questions toward persistent personal assistants that can understand, remember, and continuously learn from users' experiences.
arXiv AI
Aug 17
Evaluating Agentic Learning Harness Capabilities Without Labels via the Scaling Hypothesis
arXiv:2608. 13608v1 Announce Type: new Abstract: Agentic "Continual Learning Harnesses", systems that pair an LLM with retrieval or memory to improve from feedback without retraining, have shown growing value in cybersecurity.
arXiv AI
Aug 17
Second Thought: Reasoning in Parallel as LLM Agents Act and Observe
arXiv:2608. 13667v1 Announce Type: new Abstract: LLM agents in the ReAct paradigm alternate between reasoning, acting, and observing, but deliberate reasoning is confined to the Thought phase: while the agent serializes an action and waits for the environment, its reasoning is frozen.