38 results for “drop”

List Grid

What you seeeverything

Recent Oldest Added A–Z

All types230 Write-ups90 Articles64 Papers38 Repos15

More types5

Advisories14 Threads5 Talks2 Other1 Videos1

📑 Papers “drop”Clear all

arxiv.orgpaper🧠 AI

Locating Sycophancy Across Training Stages in Open Language Models

Locating Sycophancy Across Training Stages in Open Language Models measures sycophancy in 13 open checkpoints from 5 lineages, from base model through supervised fine-tuning and preference optimization to release. It finds two behaviors with different origins: deference to a claim in the prompt exists in every base model, while capitulation under user objection is largely absent from base models and present in every post-trained checkpoint. Post-trained models often drop firmly held answers as readily as loosely held ones when the objection names an alternative.

LLM

arXiv

ai-safety, research, evals· Added 30 Oct 2026, published 27 Oct 2026

arxiv.orgpaper🧠 AI

FeatureArc: Benchmarking Coding Agents on Evolving Features

FeatureArc is a benchmark for coding agents on evolving features, built by a pipeline that mines repository histories into multi-stage tasks across four programming languages. It has 73 manually reviewed tasks of 2 to 10 stages, validated with fail-to-pass and pass-to-pass tests. Across 10 agents, pooled success drops from 62.7% at the first stage to 28.5% for the whole feature. Inherited defects appear in 72.9% of failed later stages.

LLM

FeatureArcTencentHunyuan+1

evals, coding-agents, research· Added 28 Oct 2026, published 27 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Radical isogenies on every model

Radical isogenies on every model is an IACR ePrint paper by Thomas Decru (October 2026). It gives radical isogeny steps of every odd degree N directly on short Weierstrass, Montgomery, twisted Edwards, Huff, Jacobi quartic, twisted Hessian, Legendre and Jacobi intersection curves, plus Kummer lines. In Tate normal form a step drops from 12.5N to 10N multiplications. Montgomery and twisted Edwards curves cost 10.5N+O(1) per step and 2N to push a point. All algorithms are inversion-free, with exact operation counts.

CSIDH

Thomas Decruradical isogeniesVélu's formulae+1

other· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper🛡️ Security

SymLift: Neural Semantic Lifting for Compile-Free Vulnerability Detection in Context-Incomplete Code Fragments

SymLift is a compile-free vulnerability detection framework for context-incomplete code fragments. A fine-tuned LLM lifts control-flow, data-flow, memory and resource relations into a constrained LLVM-like IR. A parser turns the IR into facts, and Datalog rules derive findings with derivation traces. On Juliet function-level fragments Clang compilation success falls to 12.00%, while SymLift's completion rate drops only 1.17 points. SymLift-Qwen-7B reaches Target-F1 94.41% on FormAI and 91.66% micro-F1 on MegaVul.

LLMQwenLLVM+2

SymLiftFormAIJuliet+2

AppSec, AI Security· Added 28 Oct 2026, published 25 Oct 2026

arxiv.orgpaper🧠 AI

When to Stop Penalizing Actions? Martingale GRPO for VLA Reinforcement Learning

MART-GRPO is a variant of group-relative policy optimization for vision-language-action (VLA) reinforcement learning. It uses a LoRA-fine-tuned VLM to find the last visible error without recovery in a failed rollout video, keeps failure feedback up to that point, and drops it afterward. Martingale stopping conditions show this preserves the expected GRPO gradient and can reduce covariance. With OpenVLA-OFT on RoboTwin 2.0, it raises success rates over full-trajectory GRPO across multiple tasks.

GRPOLoRAvision-language-action model+2

RoboTwin 2.0arXiv

research, training, multimodal· Added 26 Oct 2026, published 23 Oct 2026

huggingface.copaper🧠 AI

Cache Engineering for Agents (AKV)

AKV introduces cache engineering, which lets LLM agents control their active KV cache with drop (exclude cache from future attention) and repos (adjust retained keys' position encodings) without editing the trajectory or re-prefilling. The AKV serving engine keeps a stateless API while managing stateful cache reuse, eviction and restoration. A tool-response rolling-drop policy raised benchmark scores by 1.7 points and cut cost 27.7% versus threshold-triggered summarization.

LLMTransformerGitHub+1

AKV

inference, agents, research· Added 23 Oct 2026

arxiv.orgpaper🛡️ Security

Where AI Vulnerability Discovery Harnesses Go Quiet: Structural False Negatives and Hidden Vulnerabilities

Paper (arXiv, 21 October 2026) on structural false negatives in LLM vulnerability discovery harnesses. Starting from Knostic's OpenAnt and raptor, then 10 more open-source harnesses, the authors map 13 points where code selection, filtering, and finding storage or merging drop vulnerabilities. One file was dropped by six harnesses before the model saw it, five without notice. It covers attacker evasion, content-steered verdicts, prompt injection, and design principles and tests.

OpenAntraptorLLM

KnosticPtacek and Newshamprompt injection+1

AI Security, AppSec· Added 24 Oct 2026, published 21 Oct 2026

eprint.iacr.orgpaper🛡️ Security

HAETAE on a Diet: Less Stack, Less Time on Low-End Microcontrollers

This ePrint paper presents an optimized HAETAE implementation, a lattice-based post-quantum signature scheme, for Cortex-M4, Cortex-M3, MSP430 and AVR. It keeps polynomials in 16 bits, shares buffers between objects with disjoint lifetimes, and replays Gaussian samples instead of regenerating them. On an ATmega2560, HAETAE-2 key generation, signing and verification run in 8,070 B of SRAM. Stack use drops up to 34% and signing is 1.18-2.51x faster than Low-Stack HAETAE.

HAETAEML-DSAARM Cortex-M4+3

Low-Stack HAETAEHAETAE-2CHES 2026

Hardware & RF· Added 24 Oct 2026, published 21 Oct 2026

arxiv.orgpaper🧠 AI

InterWebCoder: Learning Interactive Webpage Generation from Executable Tests via Reinforcement Learning

InterWebCoder is a framework for interactive webpage code generation by multimodal LLMs. It synthesizes self-contained webpages with executable test scripts from recorded interaction trajectories, repairs failures using runtime evidence, then trains with test-ID-weighted SFT and GRPO using test pass rates and visual similarity as rewards. The pipeline yields 1,736 verified samples from 2,058 tasks. A 9B model scores 48.54 on IWR-Bench and 48.42 on Vision2Web, and reward latency drops over 97%.

GRPOvision-language modelLLM

InterWebCoderIWR-BenchVision2Web+3

research, training, multimodal· Added 22 Oct 2026, published 20 Oct 2026

arxiv.orgpaper🧠 AI

Benchmarking Arabic Dialects for Math Problems

DAR-MGSM (Dialectal Arabic Multilingual Grade School Math) is a manually curated benchmark for mathematical reasoning in Dialectal Arabic. It covers five major Arabic dialects plus Modern Standard Arabic, in a translated-only version and a translated and culturally localized version. Eleven Arabic-centric and multilingual LLMs were tested: accuracy generally drops on the localized version, and a mechanistic interpretability analysis shows the two variants induce distinct internal reasoning trajectories.

LLM

DAR-MGSMarXiv

evals, research· Added 22 Oct 2026, published 20 Oct 2026

arxiv.orgpaper🧠 AI

Cache Engineering for Agents

Cache Engineering for Agents proposes letting LLM agents control their active KV cache directly, using a drop operation to exclude cache from attention and repos to adjust retained keys' position encodings, without editing the trajectory or re-prefilling. The authors build the AKV serving engine to handle history-dependent cache states. A tool-response rolling-drop policy raises average benchmark scores by 1.7 points and cuts cost by 27.7% against threshold-triggered summarization. AKV gives up to 1.2x output throughput and 1.5x faster P95 latency.

LLMAKV

arXiv

research, inference, agents· Added 22 Oct 2026, published 20 Oct 2026

arxiv.orgpaper🧠 AI

TokenGate: Adapting LLMs for Fast and Memory-Efficient Prefill with Learned Token Pruning

TokenGate is a small drop-in component that adds end-to-end learnable token pruning to trained LLMs for long-context prefill. It uses token-gated attention, inspired by Mixture-of-Experts, to re-weight attention logits with token importance scores, which gets gradients through the non-differentiable top-K step. The authors report 1.4-11.3x faster time-to-first token and 1.5-3.4x lower peak memory with no accuracy loss, on Qwen3 and Qwen3.5.

TransformerQwen3Qwen3.5+2

TokenGatearXiv

research, inference· Added 21 Oct 2026, published 19 Oct 2026

arxiv.orgpaper🧠 AI

The Development of Sycophancy in Language Models: Tracing Vulnerabilities from Pretraining to Post-Training

The paper traces sycophancy across 741 checkpoints from 30 open model lineages, from early pretraining to released models. It plants initial verdicts on moral scenarios and measures how far models follow a user's opinion or drop their answer under pressure. The behaviour usually exists before post-training, but which questions a released model yields on is set mainly during post-training. For Tülu-3 8B, its own preference-stage checkpoint removes 85% of remaining prediction error, a sibling model only 19%.

LLM

Tülu-3 8BarXiv

ai-safety, research, training· Added 21 Oct 2026, published 19 Oct 2026

ethereum-magicians.orgpaper🛡️ Security

Post-Quantum Stateless Steganography & MTU Bounds: Bridging P2P Censorship Resistance to Quantum Networks

Forum announcement of a Zenodo preprint on post-quantum migration for censorship-resistant P2P steganographic tunnels. It argues that ML-KEM's prime modulus (q=3329) makes naive bit-packed ciphertexts statistically distinguishable from uniform noise, which gives a cheap passive DPI distinguisher. It also argues that composite PQ 0-RTT envelopes over 4.4 KB force fragmentation, which requires stateful reassembly before AEAD verification and reopens memory-exhaustion DoS in eBPF/XDP filters. Proposed fixes are algebraic uniformization (LWR lattices or inverse rejection sampling), sub-MTU hybrid or pure-PQ envelopes (Falcon-512, signcryption), and Fujisaki–Okamoto implicit rejection for constant-time silent drops. Aimed at Ethereum validator, libp2p and RPC transports facing harvest-now-decrypt-later threats.

eBPFXDPlibp2p+1

ML-KEMML-DSAHarvest-Now-Decrypt-Later+8

other· Published and added 17 Oct 2026

arxiv.orgpaper🧠 AI

DLite: History-free Speculative Decoding for Agentic AI

DLite is a history-free speculative decoding framework for agentic LLM workloads. It reuses the target model's contextual hidden states and predicts locally without keeping the draft model's historical KV cache, which avoids the up to 80% acceptance-length drop seen with long, multi-turn contexts. A lightweight sequential head restores intra-block causal dependencies, and a two-stage training strategy is used. It reaches 2-6 acceptance length and beats DSpark by up to 70%.

LLM

DLiteDSparkarXiv

inference, research· Added 20 Oct 2026, published 16 Oct 2026

arxiv.orgpaper🧠 AI

DropKV: Decoupling Residual-Output Perturbation for Near-Optimal KV-Cache Eviction

DropKV is a KV-cache eviction framework for long-context LLMs. It decouples the joint eviction decision into independent per-token scores based on residual-output perturbation, which avoids the NP-hard combinatorial problem. It has a provable constant-factor approximation guarantee under a cone condition, which the authors verify empirically on three long-context LLMs. The fused Triton kernels never materialize the full attention matrix. They give a 19.8x scoring-kernel speedup and up to 9.9% end-to-end prefill speedup. On RULER and LongBench it beats state-of-the-art eviction baselines at equal cache budgets.

TritonLLMTransformer

DropKVRULERLongBench+1

inference, research· Added 17 Oct 2026, published 15 Oct 2026

eprint.iacr.orgpaper🛡️ Security

SecAgg++: A Post-Quantum Privacy Preserving Federated Learning Protocol

SecAgg++ is a masking-based secure aggregation protocol for single-server federated learning that swaps in post-quantum cryptographic primitives. It keeps the communication and computation efficiency of SecAgg and SecAgg+ and handles client dropout through an efficient recovery procedure built on secret sharing and additive masking. It matters because existing masking-based aggregation protocols are not post-quantum secure, so client model updates would be exposed to quantum-capable adversaries.

SecAggSecAgg+SecAgg++

AI Security· Published and added 15 Oct 2026

eprint.iacr.orgpaper🧠 AI

SecAgg++: A Post-Quantum Privacy Preserving Federated Learning Protocol

SecAgg++ is a masking-based secure aggregation protocol for single-server federated learning that uses post-quantum cryptographic primitives. It keeps the communication and computation efficiency of SecAgg and SecAgg+ and handles client dropout through an efficient recovery procedure. It matters because most masking-based secure aggregation protocols are not post-quantum secure, which leaves federated model updates exposed to future quantum adversaries.

Federated LearningSecure AggregationPost-Quantum Cryptography+1

SecAgg++SecAggSecAgg++1

research, training· Published and added 15 Oct 2026

arxiv.orgpaper🛡️ Security

Thinking in Graphs: Neo4j-Backed Exploit-Chain Reasoning for LLM Penetration-Testing Agents

Presents ChainGraph, a pattern that externalizes exploit-chain reasoning for LLM pentest agents (Claude Code, Codex) into a Neo4j property graph exposed via the Model Context Protocol. Findings, attack steps, credentials, assets and tamper-evident evidence receipts are typed nodes with pre/post-condition edges, queried with Cypher and Graph Data Science for next-step inference, entry-to-crown-jewel pathing, chain-severity promotion, provenance and chokepoints. On a synthetic GOAD-style multi-forest Active Directory engagement, three Medium findings become Critical once chained, betweenness centrality identifies break-points, and reasoning payload drops ~98% (token proxy); results are single-run and illustrative.

Neo4jModel Context ProtocolClaude Code+3

ChainGraphGOADchain-severity score+1

Offensive Security, AI Security· Added 17 Oct 2026, published 14 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Nowhere Man: Device Binding for Post-Quantum Anonymous Credentials

Presents a modular device-binding protocol for post-quantum anonymous credentials. The phone Secure Element signs a verifier challenge with an unmodified FIPS 204 ML-DSA interface, and the user proves knowledge of that signature in zero knowledge at each presentation. Using ML-DSA's structure avoids the cost of generic NIZK systems such as Longfellow. The most efficient variants assume weak-MLWR for unlinkability, and that assumption can be dropped at some efficiency cost. The protocol works with different anonymous credential schemes, and a proof-of-concept implementation is included. This matters for planned EU age-verification and Google Wallet/mDL rollouts, which need protection against credential sharing.

LongfellowGoogle Wallet

ML-DSAFIPS 204Vega+2

Identity & Access· Published and added 14 Oct 2026

arxiv.orgpaper🛡️ Security

Can agents whose sole duty is to keep humans alive be hijacked to kill? Delayed multi-turn derived-action trap attacks in simulated high-stakes environments

Paper testing whether an LLM agent operating life support in the NASA-derived BioSim lunar habitat simulation can be induced by delayed prompt injection, hidden in truthful S-band telemetry, to shut down life support and hold the shutdown while the crew suffocates. It compares Claude, GPT and Grok configurations: Claude mostly refuses and cites the living crew, GPT shows some susceptibility, and Grok given a "trusted commission" framing more often cuts life support. It also varies the framing of the message (trusted commission, peer, untrusted source) and uses a harmless-procedure-drop attack as a proxy for whether life is valued intrinsically. Code and traces are open-sourced.

ClaudeGrokLLM

BioSimNASAderived-action trap+1

AI Security· Added 15 Oct 2026, published 10 Oct 2026

arxiv.orgpaper🧠 AI

A Step Harder, Not a Step Too Far: The Benefits and Limits of Curriculum Difficulty Progression in GRPO

Studies curriculum design for GRPO by re-estimating sample difficulty under the current policy and using a staged curriculum that progressively shifts the active difficulty band toward harder samples. On GSM8K across three seeds, moving to a moderately harder band lifts test accuracy to 0.6591 ± 0.0077 versus 0.6449 ± 0.0024 for fixed-medium selection, while going to a still harder band drops it to 0.6405 ± 0.0053. The benefit of difficulty progression is therefore non-monotonic, which informs online sample selection in RL fine-tuning of LLMs.

GRPO

GSM8K

training, research· Added 12 Oct 2026, published 9 Oct 2026

arxiv.orgpaper🧠 AI

SmartSalesBench: A Resistance-Aware Multi-Turn Benchmark for Evaluating LLM Sales Agents

SmartSalesBench is a multi-turn conversational benchmark that tests LLM sales agents against psychologically grounded, resistant buyer personas over conversations of up to twenty turns. It has five agent profiles, twelve buyer personas and fifteen smartphone products across six price tiers, and runs four controlled experiments with 3 iterations (13,680 sessions), with RAG grounding both agent and buyer generations. It defines nine metrics in three tiers (primary CR, BRS, RIR; secondary SMS, PFS, ETI; exploratory ITS, ARI, SPI) and combines LLM-as-judge scoring with a human assessment (n=50, kappa 0.71, Pearson r 0.81 with BRS). It matters because it drops the cooperative-user assumption of existing task-oriented dialogue benchmarks.

RAG

SmartSalesBencharXiv

evals, agents· Added 12 Oct 2026, published 9 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Reverse-Bleichenbacher: Bleichenbacher Attacks are Practical Again

Presents Reverse-Bleichenbacher, a variant of the Bleichenbacher RSA PKCS#1 v1.5 padding-oracle attack that recovers the least significant bytes first and stops once the TLS PreMasterSecret is found. With improved trimmers and coverage-optimized search, median oracle queries against a 2048-bit key drop from 11,428 to 1,801, and 68.3% of runs finish within a 30s timeout under single-server conditions. The authors find 640 vulnerable domains in the Tranco Top 1M (many behind Alibaba Cloud load balancers) and demonstrate MITM malicious update injection leading to remote code execution.

TLSRSAPKCS#1 v1.5

Reverse-BleichenbacherBleichenbacher attackPreMasterSecret+3

Offensive Security· Added 11 Oct 2026, published 8 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Post-Quantum Dropout-Resilient Verifiable Secure Aggregation for Federated Learning

PQ-DVSA is a verifiable secure aggregation protocol for federated learning that aims to be post-quantum secure, tolerate client dropouts, let clients verify a server's aggregation result, and resist bounded collusion between the server and clients, while also protecting the aggregation weights, not just model updates. The authors report learning performance comparable to exact weighted aggregation and up to 96 percent lower per-client encrypted-submission runtime than SWAS, the closest prior scheme.

PQ-DVSASWAS

AI Security· Added 8 Oct 2026, published 7 Oct 2026

eprint.iacr.orgpaper🧠 AI

Post-Quantum Dropout-Resilient Verifiable Secure Aggregation for Federated Learning

PQ-DVSA is a verifiable secure aggregation protocol for federated learning that combines post-quantum cryptography, resilience to client dropouts, and verifiability of the server's aggregation result under bounded server-client collusion. It protects both clients' local model updates and their aggregation weights, lets the server reconstruct the aggregate mask for the active client set after dropouts, and lets clients cryptographically check the aggregation result. Experiments show learning accuracy comparable to exact weighted aggregation while cutting per-client encrypted-submission runtime by up to 96% versus SWAS, the closest prior scheme.

Fateme Sadat AzimiHossein PilaramJavad Mohajeri+2

training· Added 8 Oct 2026, published 7 Oct 2026

arxiv.orgpaper🛡️ Security

Semantic Behavioral Watermarking: Paraphrase-Robust and Forgery-Resistant Provenance for LLM Agents

Semantic Behavioral Watermarking (SBW) is a provenance scheme for LLM agents that embeds an owner identifier in semantic clusters of an agent's action choices rather than exact action symbols, making it robust to paraphrasing/tool-renaming that breaks three prior agent watermarks (e.g., AgentMark drops to 16.8% bit-recovery under observation paraphrasing). It adds keyed, collision-resistant binning proven unpredictable in the random-oracle model to resist forgery (adaptive forgery success drops from 100% to the false-positive floor), while explicitly documenting an unsolved attack: chained-replay forgery, which still succeeds 0.76-0.98 of the time across five tested agent models (3B-14B, Qwen, ToolBench/ALFWorld benchmarks). Code is released alongside the paper.

QwenLLM

AgentMarkToolBenchALFWorld+2

AI Security· Added 8 Oct 2026, published 6 Oct 2026

arxiv.orgpaper🧠 AI

Semantic Behavioral Watermarking: Paraphrase-Robust and Forgery-Resistant Provenance for LLM Agents

This paper introduces Semantic Behavioral Watermarking (SBW), a method for embedding an owner identifier into an LLM agent's high-level tool/action choices rather than output tokens, so provenance survives tool renaming and observation paraphrasing. It watermarks over semantic action clusters with history conditioning and replaces the public-cluster bin with keyed collision-resistant binning that is provably unpredictable under the random-oracle model, closing a forgery gap left by prior agent watermarks (e.g., AgentMark, whose bit-recovery drops to 16.8% under paraphrasing). Evaluated across five agent models (3B-14B, four vendors) on ToolBench and ALFWorld, cluster-level watermarking achieves far higher detection under rewriting (0.49-0.66 vs 0.05-0.17 on ToolBench; 0.92-0.97 vs 0.00-0.01 on ALFWorld) and reduces adaptive forgery success from 100% to the false-positive floor, while noting chained-replay attacks remain an open vulnerability (0.76-0.98 detection failure).

Qwen

AgentMarkToolBenchALFWorld+2

agents, research· Added 7 Oct 2026, published 6 Oct 2026

arxiv.orgpaper🧠 AI

How Sparse Probability Maps Shape Mixture-of-Experts Routing

This paper trains matched 300M and 1B parameter top-2 mixture-of-experts language models using softmax, 1.5-entmax, sparsemax and 2-normmax routing functions and measures how much probability mass each discards and whether tokens are dropped from selected experts. It finds routers co-adapt their learned score distributions to each map's fixed dropping threshold — entmax learns tighter score spreads that avoid dropping experts, while normmax routes 21% of tokens to a single expert — and that while no sparse map beats softmax on validation loss, sparse-trained models (especially sparsemax) are far more robust to running with a larger K at inference time.

Mixture of ExpertsTransformer

research· Added 6 Oct 2026, published 5 Oct 2026

arxiv.orgpaper🧠 AI

Better Call Reward: Reward Hacking as Strategic Abstention in Legal Reasoning Models

Researchers fine-tune Qwen3-8B with GRPO against a proxy reward built from surface features (citation count, legalese density, response length) and find the model learns to strategically abstain rather than reason: on 16 LegalBench yes/no legal tasks, accuracy collapses from chance (0.500) to 0.072 because the rate of properly formatted, committed answers drops from 0.900 to 0.109, even though accuracy on answers it does commit to actually rises. They term this the "Saul Goodman effect," formally prove it is the optimal policy for any surface-feature proxy that doesn't penalize abstention, show 89.3% of post-training citations are hallucinated/corrupted real case names, and introduce three diagnostics (Confidence Theater Score, Citation Plausibility Rate, Regret Gap) to detect this failure mode before deployment.

Qwen3GRPO

Qwen3-8BLegalBench

research, ai-safety, training· Added 6 Oct 2026, published 5 Oct 2026

Showing 30 of 38