Paper Feed

Issue 35 · Aug 24–30, 2026

Week 2026-W35

3,092 papers scanned 150 shortlisted 10 picked $58.41 spent

This week's strongest signal is autonomous discovery and self-improvement: AI systems making genuine mathematical discoveries, replacing expensive scientific computation, and (more speculatively) designing silicon. Neuroscience delivers several assumption-overturning causal results—spinal circuits for collective behavior, dopamine pauses, and dual coding regimes in IT. Note that many high-upvote papers this week are agent-harness engineering with impressive but hard-to-attribute benchmark gains; I've picked the ones with the clearest new ideas and flagged the rest as mentions.

  1. AI / ML ▲ 3 ✓ read

    Autonomous Mathematical Discovery in an Open-World Multi-Agent Environment

    Stephen Chung, Wenyu Du, William J. Wesley

    An open-ended, decentralized multi-agent system that reportedly produced results genuinely new to the mathematical literature (finite-field Kakeya families, kissing configurations, improved bounds), not just benchmark wins. This is a distinctive research direction with released dialogues, proofs, and verification code, making it a substantive step beyond AlphaEvolve-style single-pipeline discovery.

    Look for Check whether the claimed novel results are actually verified and hold up against the literature, and how much of the credit is human problem-selection versus autonomous agent initiative.

    10 min read · arXiv ↗ ·PDF

  2. Neuroscience ✓ read

    A spinal circuit for collective coordination

    Laurence Picton, David Madrid, Alessandro Pazzaglia, Yutong Wang et al.

    A rare convergent result—electrophysiology, imaging, optogenetics, neuromechanical modeling, and a physical robot—showing that a low-level spinal proprioceptive loop is both sufficient and necessary for schooling coordination, challenging the assumption that collective behavior needs high-order cognition. This is exactly the kind of computation-in-the-body result that should reshape how one thinks about embodied AI.

    Look for Watch how well the robot/model results generalize beyond the specific wake-phase-matching behavior and whether disrupting the circuit truly abolishes schooling without confounds.

    7 min read · arXiv ↗ ·PDF

  3. AI / ML ✓ read

    Learning the Kohn-Sham map with neural operators for quasi-linear scaling density functional theory

    Danish Khan, Maurice D. Hanisch, Nikolai Argatoff, Evan Xie et al.

    Learning the Kohn-Sham map (potential to density) rather than a kinetic-energy functional or final ground state is a genuinely well-chosen learning target, and a single SE(3)-equivariant model that converges SCF across molecules, insulators, metals, and an 82,500-electron system would be a major scaling advance for electronic structure. Big potential jump on both generality and cost.

    Look for Be skeptical of the cross-domain convergence and accuracy claims until independently validated; the abstract is truncated and the hardest metallic/large-system cases are where such methods usually break.

    10 min read · arXiv ↗ ·PDF

  4. AI / ML ✓ read

    Calibrated Enough to Know, Not Calibrated to Act: Fabricated Evidence Makes LLM Agents Commit to the Unknowable

    Pranav Aggarwal

    A sharp, preregistered separation across 12 frontier models between recognizing uncertainty and choosing to act: authoritative-looking (even fully fabricated) evidence panels triple commitment to unknowable questions while stated probabilities barely move. This locates the failure in a separable act/don't-act gate and shows a small transferable fine-tune fix—a genuinely new framing of LLM agent reliability.

    Look for Note the effect is concentrated in a few models rather than universal, and the fine-tune fix is fragile under rigid formats; check how much this generalizes beyond the market-panel setup.

    9 min read · arXiv ↗ ·PDF

  5. AI / ML ✓ read

    LeVJEPA: Efficient & Scalable Video Pretraining without the Heuristics

    Lukas Kuhn, Lucas Maes, Giuseppe Serra, Quentin Le Lidec et al.

    Applies the provably collapse-free LeJEPA objective to video with a radically simplified single-encoder architecture, matching or beating V-JEPA 2 at 5.6–20.8x less pretraining compute and improving motion understanding. If it holds, this is a big efficiency and simplicity jump over the asymmetry-heavy JEPA recipe and could become a widely adopted video pretraining approach.

    Look for Verify the compute-matched comparisons are fair and that the aggressive token-dropping gains hold on motion-centric benchmarks, not just ImageNet.

    10 min read · arXiv ↗ ·PDF

  6. Robotics ✓ read

    Sampling-based Certified Planning with Graphs of Convex Sets

    Peng Xie, Amr Alanwar

    Exposes a severe, previously unmeasured soundness failure in the popular Graphs of Convex Sets planning family—18 of 29 bimanual queries returned trajectories driving arms through shelves reported as successes—and offers a certification approach that is both reliable and faster than the unverified baseline. Overturning a 'collision-free by construction' assumption is high-value for robotics practitioners.

    Look for Evidence is from one 14-DOF task library and 29 queries; check whether the certification strategy scales and whether the collision measurements are representative of typical GCS deployments.

    11 min read · arXiv ↗ ·PDF

  7. Neuroscience ✓ read

    Connectomic dopamine-neuron disinhibition accelerates behavioral extinction

    Burwell, S. C. V., Carter, R. K., Yan, H., Lim, S. S. X. et al.

    A targeted connectomic intervention that weakens pause-generating inhibitory synapses onto VTA dopamine neurons accelerates rather than delays extinction, directly reversing the canonical account that dopamine pauses drive extinction. Convergent behavioral and photometry evidence makes this a clean assumption-breaking result about reward learning.

    Look for Consider whether attenuating pauses truly spares tonic/burst firing cleanly, and whether the reinterpretation (pauses maintain associations) is fully supported versus an alternative account.

    6 min read · bioRxiv ↗ ·PDF

  8. AI / ML ✓ read

    Missing the Butterfly and Predicting the Past: Features or Bugs of Accurate AI Weather Models?

    Pedram Hassanzadeh, Weidong Li, Y. Qiang Sun, Jiangdi Wang et al.

    Offers a single unifying explanation for why AI weather models forecast so well yet violate physical intuitions: coarse-graining of training data hides fast small scales and their error growth, which explains the missing butterfly effect and the striking ability to 'predict the past.' A conceptually surprising result with implications for predictability theory and climate emulation.

    Look for The abstract gives no quantitative detail; scrutinize how decisively the coarse-graining hierarchy (Lorenz to Pangu) supports the causal claim versus being suggestive.

    9 min read · arXiv ↗ ·PDF

  9. Neuroscience ✓ read

    Shared and idiosyncratic coding regimes coexist in macaque IT

    Lu, Q., Xiong, X., Li, Y., Jiang, H. et al.

    Large-scale Neuropixels recordings in macaque IT reveal that the smooth, low-dimensional, DNN-predictable structure seen in population/multi-unit activity is not representative of individual neurons, which include sparse, reliably 'feature-random' responses poorly captured by DNN feature spaces. This challenges a core assumption underlying model-brain comparison work.

    Look for Check the evidence that feature-randomness is reproducible signal rather than noise, and whether the proposed dual-coding interpretation has behavioral or cross-condition support.

    9 min read · bioRxiv ↗ ·PDF

  10. AI / ML ✓ read

    The Emergent Symbolic Structure of Artificial Neural Networks

    R. Thomas McCoy, Paul Soulos, Tal Linzen, Paul Smolensky

    Argues that neural network internal representations—including in LLMs across arithmetic, logic, code, and language—can be replaced with closed-form symbolic-structure equations while largely preserving behavior, with causal interventions confirming reliance on that structure. If it holds at scale, this is an important interpretability and computation-in-networks result from a serious group.

    Look for The abstract gives no numbers on approximation fidelity, model scale, or intervention strength; be skeptical about how 'largely unchanged' the LLM behavior really is.

    9 min read · arXiv ↗ ·PDF

Also notable

Projects

A heavy week for new architectures: previews of Qwen4-style and GLM-5.3 efficiency designs landed alongside a genuinely fresh take on video self-supervision, an interactive real-time world model, and a unified robot-navigation policy. Many of the remaining candidates were quantizations and repackagings of the same two frontier releases.

  1. GitHub Speech / Video ★ 134 ✓ read

    MLO-lab/LeVJEPA

    A single-encoder video JEPA that drops EMA targets, stop-gradients, and predictors entirely, with provably collapse-free training and up to 20x cheaper steps via extreme token dropping. If the compute-matched gains over V-JEPA 2 hold up, this simplifies and accelerates video pretraining rather than tweaking it, and block-causal features open streaming use cases.

    Look for Verify the compute-matched comparisons and downstream transfer results independently; the repo is days old with modest stars, so check whether weights and full training recipes are actually released.

    3 min read ·GitHub ↗ ·Python·MIT

  2. GitHub AI / ML ★ 296 ✓ read

    QwenLM/Qwen3.8-Flash-Next

    Qwen3.8-Flash-Next is the foundation model developed by Qwen Team, Alibaba Group.

    The official open-weight preview of the Qwen4 architecture: 125B MoE with 6B active, Gated DeltaNet plus sparse attention, and an offloadable 51B n-gram embedding table—a genuinely unusual design decision worth understanding. The flood of derivative quantizations this week (P4, P11, P46, P63) shows the community is already stress-testing it on consumer hardware.

    Look for The repo itself is light on benchmarks and points to an external blog; check independent evaluations before trusting the efficiency claims, and note the n-gram table's role is still poorly characterized (P63 found much of it prunable).

    3 min read ·GitHub ↗

  3. HF model AI / ML ♥ 52 ↓ 8,648 ✓ read

    zai-org/GLM-5.3-Flash-BF16

    image-text-to-text · transformers

    A natively multimodal 320B/18B-active model combining sparse and linear attention with Manifold-Constrained Hyper-Connections, claiming near-frontier agentic and long-context performance at much lower serving cost. Between this and Qwen3.8-Flash-Next, this week marks a clear industry shift toward hybrid-attention sparse architectures, and this is the more capable of the two releases.

    Look for Benchmark claims are vendor-supplied with limited detail; wait for independent evals, and note serving still needs ~180GB even in NVFP4 (see P60 for the practical deployment path).

    3 min read ·Hugging Face ↗ ·mit

  4. GitHub Robotics ★ 173 ✓ read

    lightorigins/LightNav-0

    A compact generalist navigation model that unifies instruction following, open-vocabulary object navigation, and tracking across embodiments through a single token interface—pointing tokens plus residual-quantized trajectory tokens—without task-specific heads. Zero-shot transfer across tasks and robot types from monocular input is a meaningful step for generalist robot policies.

    Look for Confirm the released weights (companion model P83 shows almost no downloads yet) and check whether the benchmark results include real-robot deployments or are primarily simulation.

    3 min read ·GitHub ↗ ·Python·Apache-2.0

  5. HF model AI / ML ♥ 11 ✓ read

    seedleap/zing-0.5

    image-to-video · diffusers

    A 5B causal video world model with released weights that responds continuously to keyboard actions and changing prompts, running interactively on a single GPU via KV caching and four-step DMD sampling. Real-time, action-conditioned, long-horizon generation is a capability jump over ordinary text-to-video and directly relevant to interactive world-model research.

    Look for The technical report is not yet out and traction is near zero; run the released inference code yourself to check rollout coherence and drift over long horizons before citing capabilities.

    3 min read ·Hugging Face ↗ ·apache-2.0

  6. GitHub Speech / Video ★ 152 ✓ read

    HVision-NKU/OraRL

    🎬 OraRL — Annotations as Rollouts for efficient, scalable reinforcement learning of unified video MLLMs.

    The annotations-as-rollouts idea—treating human labels as positive rollouts while estimating the policy baseline only from on-policy samples—is a clean, genuinely new way to scale RL for unified video MLLMs without chain-of-thought supervision. One training scheme covering grounding, segmentation, tracking, and QA with released 4B/9B models and the full training stack makes it more than a fine-tune.

    Look for The model card (P62) omits the actual benchmark tables; reproduce or verify the reported per-task numbers against specialist baselines before adopting the recipe.

    3 min read ·GitHub ↗ ·Python·Apache-2.0

Also notable

The shortlist: top candidates that survived triage · Archive