arXiv AI
Jun 29
ReFreeKV: Towards Threshold-Free KV Cache Compression
arXiv:2502. 16886v4 Announce Type: replace-cross Abstract: To reduce memory consumption during LLM inference, a handful of methods have been proposed for KV cache pruning.
Inference efficiency
Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv Machine Learning
Jun 29
Disentangling Continuous-Time Latent Dynamics: Identifiability of Latent SDEs via Diffusion Shifts
arXiv:2606. 28228v1 Announce Type: new Abstract: Causal representation learning for time series has developed strong identifiability results in discrete-time latent causal models, but identifiability in continuous-time latent stochastic differential equation (SDE) models remains largely open.
Hugging Face Trending Papers
Jun 29
Diagnosing and Mitigating Context Rot in Long-horizon Search
Extensive context has become the norm as Large Language Models (LLMs) are increasingly deployed in long-horizon tasks. The concern that increasing context length degrades model capabilities, known as context rot, has become a central issue for these applications.
Hugging Face Trending Papers
Jun 28
Safety from Honesty in a Disinterested AI Predictor
As AI systems become more capable, training procedures that optimize for downstream outcomes risk introducing implicit agency: goal-directed behavior that designers never specified. We present a formal safety argument for the Scientist AI (SAI) Predictor, trained to approximate the Bayesian posterior conditioned on a dataset of "epistemically contextualized" natural-language statements.
Hugging Face Trending Papers
Jun 28
The Joint Effect of Quantization and Sampling Temperature on LLM Safety Alignment: A Factorial Analysis
Modern LLM deployments routinely compress models and raise sampling temperature to reduce cost, latency, or repetition, yet safety evaluations usually treat these choices as fixed implementation details. This leaves a practical uncertainty: does a model that is safe at FP16 and greedy decoding remain safe after it is quantized and sampled stochastically, or do the two deployment knobs amplify one another?
Hugging Face Trending Papers
Jun 28
SAD-GS: Learning Reliable 3D Semantic Gaussian Fields via Dynamic Geo-Semantic Anchoring
Open-vocabulary 3D semantic Gaussian field learning relies on multi-view 2D supervision, whose semantic targets and spatial assignments are often unreliable. Across varying viewpoints, view-dependent features cause semantic identity drift, while propagated tracker masks introduce boundary leakage and identity switches.
arXiv Machine Learning
Jun 26
Epiphany-Aware KV Cache Eviction Without the Attention Matrix
arXiv:2606. 26472v1 Announce Type: new Abstract: As reasoning models emit chains of thought tens of thousands of tokens long, KV cache increasingly becomes a deployment bottleneck.
arXiv AI
Jun 26
Privacy-Aware Agent Collaboration for Dynamic VR Slice Management in 6G SD-RAN
arXiv:2606. 26123v1 Announce Type: cross Abstract: Ultra-low latency and high throughput are required for Virtual Reality (VR) services in 6G networks, which presents critical challenges for Software-Defined Radio Access Networks (SD-RANs) dynamic resource management.
arXiv AI
Jun 26
Investigating LLM's Problem Solving Capability -- a Study on Statics Questions
arXiv:2606. 26103v1 Announce Type: cross Abstract: Large Language Models (LLMs) have rapidly influenced many aspects of society, particularly education, due to their demonstrated ability to complete assignments and examinations across a wide range of subjects.
arXiv AI
Jun 26
From Clicks to Intent: Cross-Platform Session Embeddings with LLM-Distilled Taxonomy for Financial Services Recommendations
arXiv:2606. 26277v1 Announce Type: cross Abstract: Sequential user behavior modeling is widely adopted in industrial recommender systems; however, significant gaps remain in financial services, where pre-login web interactions and authenticated in-app experiences differ drastically.
arXiv AI
Jun 26
Geometric Fairness-Aware Routing for Federated Edge Networks
arXiv:2606. 26125v1 Announce Type: cross Abstract: Emerging 6G and edge-intelligent networks require effective and balanced routing algorithms among varied and spatially distributed devices.
arXiv AI
Jun 26
Low Resource Multimodal Translation of Nepali Spoken Words into Emotion-Conditioned Sign Language Avatars
arXiv:2606. 26107v1 Announce Type: cross Abstract: Sign language communication systems, that integrate emotional expression remain underexplored, particularly for low-resource languages.
arXiv AI
Jun 26
Hybrid privacy-aware semantic search: SVD-truncated document geometry and CKKS-encrypted query reranking under a restricted threat model
arXiv:2606. 26373v1 Announce Type: cross Abstract: Dense embeddings power semantic search and retrieval-augmented generation, but embedding-inversion attacks can reconstruct source text from a vector: when a vector database leaks, the documents behind it leak too.
arXiv AI
Jun 26
NebulaExp-8B: An Empirical Post-Training Pipeline via Full-Scale Ablation Research
arXiv:2606. 26671v1 Announce Type: new Abstract: Post-training alignment determines the reasoning and human preference following capabilities of large language models, yet most existing works withhold detailed data construction, filtering rules and training recipes, which hinders community reproducibility and lightweight model optimization.
arXiv Machine Learning
Jun 26
ProtoKV: Streaming Video Understanding under Delayed Query with Summary-State Memory
arXiv:2606. 26762v1 Announce Type: cross Abstract: Streaming video understanding (SVU) must answer queries that arrive asynchronously while visual tokens stream continuously under strict GPU-memory and query-time latency budgets.
arXiv Machine Learning
Jun 26
DanceOPD: On-Policy Generative Field Distillation
arXiv:2606. 27377v1 Announce Type: cross Abstract: Modern image generation demands a single model that unifies diverse capabilities, including text-to-image (T2I), local editing, and global editing.
arXiv AI
Jun 26
CARVE: Content-Aware Recurrent with Value Efficiency for Chunk-Parallel Linear Attention
arXiv:2606. 27229v1 Announce Type: cross Abstract: Recurrent models must forget in order to remember, yet the state of the art decides what to erase without consulting what is stored -- the gate sees only the arriving token, not the memory it is about to modify.
arXiv AI
Jun 26
SKILL-DISCO: Distilling and Compiling Agent Traces into Reusable Procedural Skills
arXiv:2606. 26669v1 Announce Type: new Abstract: Agents often repeatedly solve similar task instances from scratch, leading to unnecessary reasoning cost and long execution traces.
arXiv AI
Jun 26
Risk-Aware Selective Multimodal Driver Monitoring with Driver-State World Modeling
arXiv:2606. 26922v1 Announce Type: cross Abstract: Continuous driver monitoring in automated vehicles requires low-latency inference while avoiding unsafe decisions under uncertain driver states.
arXiv AI
Jun 26
Geometry-Aware MCTS for Extremal Problems in Combinatorial Geometry
arXiv:2606. 26399v1 Announce Type: new Abstract: We study certain extremal problems in combinatorial geometry that ask about configurations of points in an $n \times n$ grid that satisfy strict, global geometric constraints.