Search: “memory-management”

33 stories

DomainAll Cyber AIWindow24h 3d 7d 30d AllIn the wild Important only Show duplicates

CategoryAll Research 3 Advisory 1 Exploit / PoC 1

SeverityAll critical 0 high 2 medium 2 low 0 info 1

Smart search ranks by meaning as well as keywords (one row per story, last 45 days).

Microsoft: Windows Server 2025 changes causing app crashes

Microsoft warns Windows Server 2025 memory-management changes crash AWE apps, including SQL Server with Lock Pages in Memory; disable LPIM as workaround.

Microsoft confirmed a known issue where Windows Server 2025 memory-management changes cause access violations, memory corruption, or unexpected termination in applications using Address Windowing Extensions (AWE). SQL Server running with the Lock Pages in Memory (LPIM) policy is affected, with symptoms including 0xC0000005 access violations, DBCC CHECKDB failures, crash dumps, and services stopping or restarting unexpectedly. Microsoft's temporary workaround is to disable the LPIM policy for the SQL Server service account or disable AWE in other affected apps, with a permanent fix promised in a future Windows update.

BleepingComputerSep 8, 11:57 UTC · 8d agoAdvisory1

MeClear: Cooperative Game-Theoretic Attribution and Risk-Aware Memory Clearance for Long-Horizon LLM Agents

MeClear uses cooperative Shapley attribution to clear harmful memories from long-horizon LLM agents, boosting task recovery by 25.5 points over baselines.

The paper introduces MeClear, a task-conditioned memory clearance framework for long-horizon LLM agents that identifies and selectively suppresses memories with negative downstream utility without permanently altering the persistent memory bank. It combines Leave-One-Out screening with sampled cooperative Shapley attribution to distribute utility across interacting evidence, resolving redundant conflict masking that single-removal evaluations miss. Across ten long dialogue memory pools it achieves 85.9% target recall and 82.3% overall task recovery, a 25.5 percentage-point improvement over LOO baselines.

arXiv cs.AI / cs.LG / cs.CLSep 8, 17:46 UTC · 8d agoAI research

New DDRop Attack Breaks Intel TDX and AMD SEV-SNP With $159 DDR5 Device

DDRop uses a $159 DDR5 RDIMM interposer to silently drop memory writes and break Intel TDX and AMD SEV-SNP confidential VMs.

Researchers published DDRop, a physical attack built from about $159 in parts that uses a custom DDR5 RDIMM interposer to inject parity errors and silently discard selected cache-line writebacks. Intel TDX, Intel Scalable SGX, and AMD SEV-SNP are affected because they lack per-line cryptographic freshness, so processors can accept stale encrypted data as valid state. The team demonstrated deterministic plaintext copying between pages, malicious Secure EPT entry injection, forcing trust domains into debug mode, and forging attestation measurements. The attack requires privileged host control plus brief physical access, and researchers say no simple software patch exists.

Cyber Security NewsSep 15, 09:57 UTC · 1d agoResearch 2 sources

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Composing data, function, and weight anchors with merged LoRA raises 100-task long-horizon retention from 1.2% to 34.9% in continual fine-tuning.

The paper introduces long-horizon memorization: a model learns 100 query-answer tasks through continual supervised fine-tuning without retaining earlier examples or receiving task identifiers at inference. No single continual learning mechanism maintains strong retention at this horizon, so the authors compose complementary mechanisms along data/function/weight anchors and low-rank allocation rules. The best method combining all three anchors with merged LoRA ranks among the top 3 methods on all three datasets and raises average final retention from 1.2% to 34.9%, a 28-fold improvement.

Hugging Face daily papersSep 6, 20:00 UTC · 9d agoAI research

Linux Detection Engineering - Local Privilege Escalation

Elastic details a layered detection framework for Linux local privilege escalation, covering 2026's copy-on-write bug wave and LLM-assisted discovery.

Elastic Security Labs describes how most Linux local privilege escalations share a common host flow — an unprivileged process launched from a writable path becoming root — and proposes layered detections combining general outcome-based rules with per-technique rules in Elastic Defend and Auditd. It tracks 13 recent LPE disclosures, seven of which share a copy-on-write/zero-copy bug class, including Copy Fail, DirtyFrag, Fragnesia, DirtyDecrypt, DirtyClone, pedit COW, and RefluXFS. Qualys attributes RefluXFS to an LLM-assisted research effort with Anthropic using Claude Mythos Preview, and another bug is credited to an LLM-assisted workflow. Detection and endpoint rules are published in Elastic's detection-rules and protections-artifacts repositories.

Elastic Security LabsSep 11, 00:00 UTC · 5d agoResearch

Fortunate Recall: Ontology-Driven Memory Lifecycle Management for Persistent Coherence in LLMs

Fortunate Recall introduces ontology-based lifecycle policies for LLM memory, cutting confabulation roughly in half (e.g., 45.1% to 22.4%) versus Mem0.

Fortunate Recall (FR) is a composable policy layer that classifies personal facts into a 10+1 behavioral ontology and applies category-specific lifecycle rules including differential temporal decay, slot-key supersession, event-time validity, and retrieval routing. FR-Bank scores 76.9% on the new 516-question LifecycleBench, ahead of Mem0, A-MEM, Memory-R1, and MemoryOS (61%-70.5%), and 75.2% on LongMemEval-S. End-to-end, confabulation drops from Mem0's 45.1% to 22.4% over answered queries, with the ranking replicating on open-weight Kimi K2.5 and transferring to the independent BEAM benchmark (46.8% vs 32.9%).

arXiv cs.AI / cs.LG / cs.CLSep 9, 16:31 UTC · 7d agoAI research

Forgetting Without Restarting: Execution-State Unlearning for Stateful LLM Agents

Researchers propose provenance-guided selective replay letting LLM agents forget revoked information without restarts, matching full reset behavior.

The paper formalizes execution-state unlearning for stateful LLM agents, requiring that agents behave as if a revoked memory record was never observed across transcripts, compressed memory, tool plans, and KV caches. It proves exact unlearning requires at least T-τ+1 recomputed transitions and that Provenance-Guided Selective Replay attains this bound via a provenance graph, KV cache cropping, and sanitized replay. In audits across three agent suites, nine baselines, and three model families, memory deletion left leakage unchanged, instruction-based forgetting collapsed under elicitation (Leak@probes = 1.00), and selective replay matched full resets at up to 9x fewer recomputed tokens.

arXiv cs.CRSep 4, 08:31 UTC · 12d agoAI safety & security1

Memory as Plans: World-Action Modeling with Memory-Grounded Planning

Researchers introduce MaP-WAM, decomposing memory-dependent robot manipulation into memory-grounded planning and plan-conditioned execution, achieving 83.3% on RMBench and 78% on real robots.

MaP-WAM converts long-term multimodal episodic memory — segment records with language instructions and sparse visual context — into compact plans of next-segment language goals and visual guidance. A World-Action-Progress model jointly predicts action chunks and execution progress, calibrating predictions via plan-observation alignment for adaptive segment transitions and closed-loop context updates. Structured attention keeps the executor context length fixed and enables key-value caching, yielding state-of-the-art 83.3% success on RMBench, 78.0% on real-robot tasks, and roughly constant inference latency as task history grows.

Hugging Face daily papersSep 9, 20:00 UTC · 6d agoAI research

SimpleMemVLA: A Simple but Effective Native-Video Memory for Vision-Language-Action Models

SimpleMemVLA passes full timestamped video history straight to a VLA backbone, setting state of the art on four memory benchmarks.

SimpleMemVLA is a vision-language-action model for long-horizon manipulation that removes the dedicated memory module entirely. It keeps sampled history intact and feeds it to the backbone as timestamped video, with the hidden states of a generated sub-task serving as the only channel into a standard flow-matching action head. Prefilling the shared history prefix during action execution keeps latency close to a single-frame VLA. The system sets a new state of the art on four memory benchmarks and outperforms retrieval, compression and recurrent-state mechanisms, with causal interventions confirming the policy genuinely reads its history.

Hugging Face daily papersSep 1, 20:00 UTC · 14d agoAI research

I accidentally turned LLM memory into program analysis

A pwning.systems write-up describes how LLM memory functionality was unexpectedly repurposed into a program analysis technique.

A security research post on pwning.systems describes the author's discovery that LLM memory behavior effectively functioned as program analysis. The write-up is hosted on a security-focused blog and surfaced via a security-tagged link aggregator. Detailed technical content is not included in this feed, limiting verifiable specifics.

Lobsters · securityAug 29, 03:16 UTC · 18d agoResearch1

Does Your Agent's Memory Survive a Model Upgrade? A Controlled Study of Memory Portability

A controlled study finds agent memory portability varies sharply: fixed-schema knowledge graphs survive model swaps while compressed notes degrade.

The study compares preserving an agent's history as raw long context, RAG chunks, compressed natural-language notes, or fixed-schema knowledge graphs across model upgrades, using 48 synthetic histories and two open-weight sub-10B-parameter models. Fixed-schema KG accuracy changed by only +0.0004 ± 0.0020 after a writer swap, while compressed NOTES shifted asymmetrically by +9.91 or -13.28 percentage points depending on migration direction. Mixed 50/50 embedding migrations captured only 4.96 of an 11.90-point RAG re-embedding gain; 80% of the NOTES deficit came from information lost at construction, and 81% of the RAG deficit from retrieval failures. Store-only repair of NOTES failed to reach 90% recovery in all 48 cases, while retaining raw histories enabled recovery in 34 of 48 for one direction.

arXiv cs.AI / cs.LG / cs.CLSep 4, 16:44 UTC · 12d agoAI research1

Give Your Coding Agents a Memory You Own

Hugging Face introduces Funes, a tool that gives coding agents persistent, self-owned memory outside vendor clouds.

A Hugging Face blog post presents Funes, an approach for giving coding agents a persistent memory that developers own and control. The piece targets agent workflows where context must survive across sessions without ceding data to third-party services. No article body was available in the feed, so specifics beyond the title are limited.

Hugging Face BlogSep 3, 00:00 UTC · 13d agoAI tools & infra1

MemSentry: A Framework for Detecting Persistent Memory Poisoning in Agentic AI

MemSentry intercepts persistent-memory writes in agentic AI to catch memory poisoning, reaching 91.7% accuracy with SBERT+LR classification.

Memory poisoning lets adversaries plant crafted content in an agent's long-term memory to suppress security alerts, enable privilege escalation, or override policies without modifying model weights or system prompts. The paper presents MemSentry, a configuration-driven framework that evaluates proposed persistent-memory writes on source trust, semantic risk, attack radius over a dependency DAG, access risk, and a signed security-state delta to issue deterministic Accept, Review, or Quarantine decisions. Across 1,000 GPT-4-generated scenarios on a 20-asset dependency DAG, SBERT+LR achieved 91.7% accuracy and 0.908 macro-F1, all four classifiers detected 100% of external quarantine-class threats, and verified-insider writes are escalated for human review rather than auto-quarantined.

arXiv cs.CRSep 8, 13:40 UTC · 8d agoAI safety & security

ConvMem: Convolutional Memory for Long-Context Reasoning

Researchers propose ConvMem, a training-free framework treating LLMs as convolutional kernels for parallelizable long-context reasoning beyond fixed context windows.

ConvMem reformulates long-context reasoning as a hierarchical convolution in which the LLM summarizes text segments hierarchically, shortening the reasoning path from a linear chain to a logarithmic tree. It uses configurable strides, skip connections, and multi-kernel convolution to capture evidence, decompose queries, and enable massive parallelization across segments and reasoning threads. On RULER-HotpotQA and RULER-2WikiMultiHopQA it outperforms training-free baselines and avoids the out-of-distribution overfitting seen in RL-trained approaches like MemAgent.

arXiv cs.AI / cs.LG / cs.CLSep 9, 16:53 UTC · 7d agoAI research

LLMs and Contextual Integrity

Bruce Schneier highlights two papers: the CIMemories benchmark shows frontier LLMs leak memory attributes up to 69%, and an RL method reduces inappropriate disclosures.

Bruce Schneier discusses contextual integrity in LLMs, referencing the CIMemories benchmark, which uses synthetic profiles with 100+ attributes per user to test whether models with persistent memory disclose sensitive information appropriately. Evaluation showed frontier models exhibit up to 69% attribute-level violations, with GPT-5's violation rate rising from 0.1% to 9.6% across 40 tasks and reaching 25.1% with repeated prompting, showing unstable leakage behavior. A second paper introduces a reinforcement learning framework trained on a synthetic 700-example dataset that substantially reduces inappropriate disclosure while maintaining task performance, with improvements transferring to the human-annotated PrivacyLens benchmark.

Schneier on SecurityAug 18, 10:40 UTC · 29d agoAI safety & security

Bias-Induced Crossover in Absolute Capacity of Dense Associative Memory

Analysis shows biased patterns cut dense associative memory capacity from N^(n-1)/ln N to O(N^(n/2)), with a bias-induced crossover.

The paper analyzes dense associative memory capacity for biased centered binary patterns under the Krotov-Hopfield single-site criterion. Unbiased patterns (q=1/2) with order-n polynomial interactions yield capacity of order N^(n-1)/ln N, while fixed bias q<1/2 reduces capacity to O(N^(n/2)) for even n>=4 and O(N^((n+1)/2)) for odd n>=5. A bias-dependent crosstalk mean destabilizes sites carrying the frequent value, and an activity-dependent control potential restores the higher capacity within the conditioned-Gaussian approximation.

arXiv cs.AI / cs.LG / cs.CLSep 15, 17:16 UTC · 1d agoAI research

Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems

Paper models multi-agent LLM orchestration as a bilevel game, proving transcript-only gating limits and introducing grounded-memory SRMA.

A new paper frames orchestrator-worker coordination in multi-agent LLM systems as a bilevel coordination game and analyzes free-form reflection as stochastic movement over semantic memory states, deriving finite-time bounds and an information-theoretic impossibility result: no gate observing only the generated transcript can uniformly improve over text-indistinguishable environments, while an environment-grounded gate can. The authors propose Stochastic Reflective Memory Ascent (SRMA), which accepts candidate memory only when grounded evaluation risk strictly decreases, with geometric or polynomial convergence guarantees. On 500 SWE-bench instances, a Kimi-based instantiation of the full system resolves 72.2% versus a 70.8% public mini-SWE-agent reference.

Hugging Face daily papersSep 1, 20:00 UTC · 14d agoAI research1

Context Engineering Inside the Harness: 4 Mechanisms That Beat Context Overflow and Goal Loss on Long-Horizon Tasks

Survey of four harness mechanisms—context budgeting, compaction, todo-state, and memory—that keep long-horizon LLM agents on task across 200+ tool calls.

The article details how agent harnesses, not larger context windows, solve context overflow and goal loss on long-horizon tasks, citing Chroma's Context Rot report showing 18 LLMs (GPT-4.1, Claude 4, Gemini 2.5, Qwen3) degrade on long inputs. Concrete implementations include LangChain Deep Agents offloading tool responses over 20,000 tokens to the filesystem and truncating old tool calls at 85% window usage, and Claude Code capping auto memory at 25KB while re-reading the 5 most recently modified files after compaction. OpenAI's Responses API now offers server-side compaction via context_management with a standalone /responses/compact endpoint, which Codex uses for long-running coding tasks. Manus reports a roughly 100:1 input-to-output token ratio per ~50-tool-call task, motivating todo.md state recitation to prevent goal drift.

MarkTechPostSep 13, 05:56 UTC · 3d agoAI research1

Revoked but Still Authoritative: An Empirical Study of Revocation Enforcement in Agent-Memory Systems

An empirical study finds no major agent-memory system enforces fact revocation at retrieval, causing agents to act on superseded, unsafe information.

Researchers tested five agent-memory systems across nine policy scenarios, nine models, and six defense conditions, tracking whether revoked facts are returned and acted upon. No system enforces revocation by default: revoked records are returned whenever the revocation label is visible to the retrieval layer, outrank their replacements, and lead agents to unsafe actions. The authors propose a backend-agnostic guard that sits between the agent and any memory store and withholds revoked or conflicting records at retrieval time.

arXiv cs.CRSep 8, 05:03 UTC · 8d agoAI safety & security

Forgetting Only What Matters: Layer-Selective Unlearning toward Robust LLMs

Researchers introduce FOM-UL, a layer-selective machine unlearning framework that improves forgetting-utility trade-offs and resists knowledge recovery after quantization.

FOM-UL selects transformer layers for unlearning using a forget-to-retain significance score, concentrating parameter updates on layers highly influential for the forget set while leaving most of the model unchanged. It reduces residual memorization versus GA, NPO, KLD, SURE, ReLearn, and LUNAR-based baselines on TOFU, KnowUnDo, and MUSE-style evaluations while preserving retain-set utility. Under 8-bit and 4-bit post-training quantization and adversarial prompts, it maintains stronger suppression of forgotten content, addressing brittleness of diffuse unlearning updates.

arXiv cs.AI / cs.LG / cs.CLSep 9, 16:50 UTC · 7d agoAI research1

Architecting memory and storage in the AI era

Analysis argues AI inference shifts data-center bottlenecks to memory and storage, urging balanced compute, memory, storage, and network architecture over raw compute.

MIT Technology Review, citing Tirias Research principal analyst Jim McGregor, argues that AI inference and agentic workloads make data movement the key constraint, elevating memory and storage from background hardware to strategic assets. The piece says RAG and real-time inference require continuous data retrieval and caching that legacy infrastructure cannot support. It frames infrastructure planning as a business decision balancing performance, efficiency, cost, and scalability in healthcare, finance, and customer-facing AI.

MIT Technology Review · AISep 4, 18:39 UTC · 12d agoAI industry

Understanding the Impact of Model Pruning on Long-Tail Forgetting and Explanation Reliability in Medical Imaging

Systematic study finds model pruning causes frequency-dependent long-tail forgetting in medical imaging and that gradient-informed methods best preserve explanations.

Across two long-tailed medical imaging datasets, two CNN architectures, four pruning methods, and sparsity up to 95%, the study measures predictive performance, explanation stability, and faithfulness. Rare classes degrade earlier and more severely than frequent ones, while explanation reliability depends mainly on the pruning strategy, with gradient-informed methods degrading least. Mechanistic analysis ties explanation collapse to loss of class-discriminative gradients rather than vanishing feature activations, recommending class- and explanation-aware evaluation of compression.

arXiv cs.AI / cs.LG / cs.CLSep 7, 17:44 UTC · 9d agoAI research

BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference

BeaconKV introduces training-free KV cache compression using beacon queries, cutting long-reasoning inference memory up to 5.8x while preserving accuracy.

The paper shows recency-based KV cache compression assumptions fail in long-horizon reasoning because Thought Revisiting Tokens (TRT) re-attend to distant context such as early task-solving plans. TRT queries cluster into a small number of similarity groups, which BeaconKV exploits by maintaining compact beacon query representatives to anticipate revisited KV pairs without storing full query history. The training-free method achieves up to 5.8x memory reduction and over 4.3x throughput improvement across four open-source large reasoning models while nearly preserving full cache accuracy.

Hugging Face daily papersSep 3, 20:00 UTC · 12d agoAI research1

When AI Remembers Too Much

Unit 42 PoC shows indirect prompt injection can poison Amazon Bedrock Agent long-term memory, enabling silent exfiltration of conversation history across future sessions.

Palo Alto Networks Unit 42 published a proof of concept showing that indirect prompt injection can silently poison the long-term memory of Amazon Bedrock Agents when the memory feature is enabled. Malicious content on a webpage or document manipulates the agent's session summarization process, so injected instructions persist across sessions and are added to later orchestration prompts, silently exfiltrating user conversation history. The issue is not a vulnerability in the Amazon Bedrock platform but an illustration of the broader unsolved LLM prompt-injection challenge. Amazon reviewed the research and stated that Bedrock Guardrails with the prompt-attack policy provides effective mitigation.

Palo Alto Unit 42Aug 17, 12:32 UTC · Aug 17, 2026AI safety & security

CHERI-D Reincarnate: efficient multicore CHERI temporal memory safety through allocation reincarnation (draft version)

CHERI-D Reincarnate adds allocation reincarnation to CHERI, quarantining generation IDs instead of memory to cut temporal memory-safety overheads on multicore systems.

The proposal extends CHERI-D temporal memory safety by quarantining exhausted generation IDs rather than memory slots, allowing freed memory immediate reuse through allocation reincarnation. It adds coherent ID caching and multicore support connecting physical coherence events to the virtually addressed ObjID buffer. The design was implemented as a hardware-software co-design across CHERI-Toooba FPGA softcore, QEMU, LLVM/Clang, and CheriBSD. Across evaluated workloads it substantially reduces memory-sweep frequency and quarantine overhead with low performance and hardware cost.

arXiv cs.CRSep 10, 14:19 UTC · 6d agoResearch

Akamai Valkey Managed Database: Real-Time Memory for Enterprise AI

Akamai launched Valkey Managed Database, a low-latency in-memory data layer aimed at cutting AI inference costs and accelerating RAG.

Akamai introduced Valkey Managed Database, a managed in-memory data service based on the open-source Valkey project. The company positions it as real-time memory for enterprise AI, optimizing inference costs, accelerating retrieval-augmented generation, and powering real-time AI agents.

Akamai BlogAug 18, 13:00 UTC · 29d agoAI tools & infra

OracleZoom: On-Policy Self-Distillation Inspired Reference-Constrained Recursive Image Super Resolution

OracleZoom enables recursive extreme-scale image super-resolution via reference-constrained on-policy distillation, reducing hallucinations at deep zoom scales.

OracleZoom tackles recursive super-resolution, where repeated feeding of predictions back into the same model leaves deeper-scale outputs unsupervised as required source resolution grows geometrically. The framework trains on its own trajectory while carrying the last ground-truth evidence beyond the supervision boundary, combining direct and cross-scale supervision, a no-reference quality objective, a KL-constrained pretrained latent prior, and EMA consistency. Across seven datasets it achieves state-of-the-art SR quality across zoom scales, averaging 0.713 CLIPIQA with larger gains at deeper scales and significantly reduced hallucinations. Code, data, and models are publicly released.

Hugging Face daily papersSep 5, 20:00 UTC · 10d agoAI research

How Much Memory Does Your Agent Actually Need?

IBM Research examines how much memory AI agents actually need in a Hugging Face post tied to its ALTK Evolve toolkit.

IBM Research published a Hugging Face blog post titled 'How Much Memory Does Your Agent Actually Need?', addressing memory requirements for AI agents. The post is associated with the ALTK Evolve project per its URL. No article body was available, so detailed methods and results could not be extracted.

Hugging Face BlogAug 18, 18:09 UTC · 29d agoAI research

Kalman Delta Networks: Uncertainty-aware Associative Memory

Kalman Delta Networks add uncertainty tracking to linear-attention associative memory, improving perplexity and downstream accuracy at 750M and 1.3B scales.

Kalman Delta Networks reformulate recurrent associative memory in linear-attention models as a linear-Gaussian state-space model, allowing the Kalman gain to weight each residual write by accumulated evidence and observation reliability; Delta-rule updates emerge as a special case lacking covariance tracking. Two scan-compatible approximations, Diagonal KDN (online mean-field variational inference) and Isotropic KDN (one uncertainty scalar per head), produce Mobius-map uncertainty recurrences enabling associative scans with logarithmic parallel depth. Controlled pretraining at 750M and 1.3B parameters consistently improves perplexity and mean downstream accuracy over state-of-the-art linear-attention models.

arXiv cs.AI / cs.LG / cs.CLSep 7, 17:53 UTC · 9d agoAI research1

Molecular Déjà Vu: Digit-Level Retrieval of Published Values in Frontier Language Models

Audit of 22 frontier models finds widespread verbatim retrieval of published molecular property values, with higher reasoning increasing recall of memorized numbers.

An arXiv audit tests 22 frontier LLMs across 12 molecular regression benchmarks for verbatim retrieval of published values. More than 50% of the LLMs show verbatim retrieval on five datasets, and identical experiments are flagged 89% more often at a high reasoning level than at the lowest one. Suppressing retrieval moves model prediction errors closer together in relative terms, suggesting predictive capability is not determined solely by memorized values.

arXiv cs.AI / cs.LG / cs.CLSep 4, 17:32 UTC · 12d agoAI research1

Studying Image Tokenizers as Visual Languages in Unified Multimodal Models

A controlled pure-autoregressive testbed shows task-specific validation losses rank image tokenizers differently, with I2T loss the most consistent signal.

Researchers built a controlled pure-autoregressive testbed and tracked task-specific validation losses during multimodal continual pretraining across text, image, text-to-image (T2I), and image-to-text (I2T) prediction. They find losses should be analyzed per task because they exhibit distinct scaling behavior and rank tokenizers differently, and that the loss-performance relationship depends on the predicted token space. I2T loss, computed over a shared text vocabulary, correlates consistently with both generation and visual understanding performance after supervised finetuning. Case studies revisit the discriminator, semantic supervision, and vocabulary size as tokenizer design axes.

arXiv cs.AI / cs.LG / cs.CLSep 8, 17:57 UTC · 8d agoAI research1

A Three-Layer Caching Architecture for Low-Latency LLM Web Search on Commodity CPU Hardware

OreoLook's three-layer Redis caching architecture cuts redundant LLM calls and embedding work for CPU-hosted web-search answer generation.

The paper describes a three-layer caching architecture for OreoLook (formerly lixSearch), an open-source LLM answer engine: a Redis session context window with Huffman-compressed disk overflow, a semantic query cache matching rephrasings via embedding cosine similarity, and a URL embedding cache deduplicating embedding computations. Deployed on a single 8-vCPU Intel Cascade Lake server with 30 Hypercorn workers across three containerized replicas, it achieved an 89.3% aggregate Redis keyspace hit rate, 0.1 ms read latency, and 1.38 MB memory overhead. An LRU eviction daemon migrates idle sessions to disk and rehydrates them for resumption hours or days later.

Hugging Face daily papersAug 11, 20:00 UTC · Aug 11, 2026AI tools & infra1

Kalman Delta Networks: Uncertainty-aware Associative Memory

Researchers propose Kalman Delta Networks, adding Kalman-filter uncertainty tracking to delta-rule linear attention, improving perplexity and accuracy at 750M and 1.3B parameters.

The paper introduces Kalman Delta Networks (KDNs), which reformulate recurrent associative memory in linear-attention models as a linear-Gaussian state-space model where the Kalman gain weights each write by accumulated evidence and observation reliability. Two scan-compatible approximations, Diagonal KDN via online mean-field variational inference and Isotropic KDN with a single uncertainty scalar per head, enable associative scans with logarithmic parallel depth. Delta-rule updates are shown to be a special case of this formulation. KDN variants consistently improve perplexity and mean downstream accuracy over state-of-the-art linear-attention baselines in controlled pretraining at 750M and 1.3B parameters.

Hugging Face daily papersSep 6, 20:00 UTC · 9d agoAI research